BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Hung-yi Lee

Hung-yi Lee contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
eess.ASComputation and LanguageSoundMachine LearningArtificial IntelligenceCryptography and SecurityInformation Retrieval

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
60works
0followers
7topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

60 published item(s)

preprint2026arXiv

From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data

Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs. These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks. This adaptation process presents two major limitations. First, ALLMs often suffer from catastrophic forgetting, where crucial textual capabilities like instruction-following are lost after training on audio data. In some cases, models may even hallucinate sounds that are not present in the input audio, raising concerns about reliability. Second, achieving cross-modal alignment between audio and language typically relies on large collections of task-specific question-answer pairs for instruction tuning, making it resource-intensive. To address these issues, previous works have leveraged the backbone LLMs to synthesize general-purpose, caption-style alignment data. In this paper, we propose a data generation framework that produces contrastive-like training data, designed to enhance ALLMs' ability to differentiate between present and absent sounds. We further extend our approach to multi-audio scenarios, enabling the model to either explain differences between audio inputs or produce unified captions that describe all inputs, thereby enhancing audio-language alignment. We refer to the entire ALLM training framework as bootstrapping audio-language alignment via synthetic data generation from backbone LLMs (BALSa). Experimental results indicate that our method effectively mitigates audio hallucinations while reliably maintaining strong performance on audio understanding and reasoning benchmarks, as well as instruction-following skills. Moreover, incorporating multi-audio training further enhances the model's comprehension and reasoning capabilities. Overall, BALSa offers an efficient and scalable approach to developing ALLMs.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

MMMOS: Multi-domain Multi-axis Audio Quality Assessment

Accurate audio quality estimation is essential for developing and evaluating audio generation, retrieval, and enhancement systems. Existing non-intrusive assessment models predict a single Mean Opinion Score (MOS) for speech, merging diverse perceptual factors and failing to generalize beyond speech. We propose MMMOS, a no-reference, multi-domain audio quality assessment system that estimates four orthogonal axes: Production Quality, Production Complexity, Content Enjoyment, and Content Usefulness across speech, music, and environmental sounds. MMMOS fuses frame-level embeddings from three pretrained encoders (WavLM, MuQ, and M2D) and evaluates three aggregation strategies with four loss functions. By ensembling the top eight models, MMMOS shows a 20-30% reduction in mean squared error and a 4-5% increase in Kendall's τ versus baseline, gains first place in six of eight Production Complexity metrics, and ranks among the top three on 17 of 32 challenge metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation

Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior literature, these models are often evaluated using ``global token perplexity'', which directly applies the text perplexity formulation to speech tokens. However, this practice overlooks fundamental differences between speech and text modalities, possibly leading to an underestimation of the speech characteristics. In this work, we propose a variety of likelihood- and generative-based evaluation methods that serve in place of naive global token perplexity. We demonstrate that the proposed evaluations more faithfully reflect perceived generation quality, as evidenced by stronger correlations with human-rated mean opinion scores (MOS). When assessed under the new metrics, the relative performance landscape of spoken language models is reshaped, revealing a significantly reduced gap between the best-performing model and the human topline. Together, these results suggest that appropriate evaluation is critical for accurately assessing progress in spoken language modeling.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

On the social bias of speech self-supervised models

Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where algorithms potentially amplify disparate properties between social groups present in the data used for training. Bias in SSL models can perpetuate injustice by automating discriminatory patterns and reinforcing inequitable systems. This work reveals that prevalent SSL models inadvertently acquire biased associations. We probe how various factors, such as model architecture, size, and training methodologies, influence the propagation of social bias within these models. Finally, we explore the efficacy of debiasing SSL models through regularization techniques, specifically via model compression. Our findings reveal that employing techniques such as row-pruning and training wider, shallower models can effectively mitigate social bias within SSL model.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

ReMedi: Reasoner for Medical Clinical Prediction

Predicting future clinical outcomes from electronic health records (EHR) remains challenging due to the complexity and heterogeneity of patient data. LLMs have shown strong potential for such predictive tasks, yet existing approaches mainly focus on enhancing medical knowledge through distillation or RAG while relying on the model's internal ability to interpret contextual information. In this work, we present ReMedi (Reasoner for Medical Clinical Prediction), a framework for improving clinical outcome prediction from EHR. ReMedi generates rationale-answer pairs using a challenging sample regeneration mechanism for complex clinical questions, which leverages ground-truth answers as hints to enhance reasoning for further fine-tuning and preference tuning. ReMedi integrates ground-truth outcome guidance into the preference data construction loop, regenerating rationale-answer variants. By tuning on these rationale-answer pairs, the model improves its predictive performance. Experiments on multiple EHR prediction tasks demonstrate substantial gains of up to 19.9 percent over state-of-the-art baselines in terms of F1 score, underscoring ReMedi's effectiveness in real-world clinical prediction.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts

Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must be consumed in order. We challenge both assumptions through a systematic intervention pipeline--removal, masking, shuffling, and noise injection--applied to model-generated reasoning chains across three models and three benchmarks. Our findings are counterintuitive on three dimensions. Order: Does the sequential order of a reasoning chain matter for answer extraction? No--line-level shuffling reduces accuracy by less than 0.5 pp; word-level shuffling retains 62%-89% accuracy; only token-level shuffling collapses to near zero. Pretrained-only and instruction-tuned variants exhibit near-identical tolerance (78.67% vs. 78.00% under line shuffling), indicating order-independence originates from pretraining rather than reasoning-specific fine-tuning. Dense: Is all the information in a reasoning chain important for answer extraction? No--masking numeric digits collapses accuracy to exactly 0%, while masking alphabetic prose improves accuracy by 4.7 pp. Robustness: Is a reasoning chain that is both order-shuffling and non-dense still robust? Yes--the most aggressively reduced representation (all natural language removed, lines arbitrarily shuffled) still achieves 83% accuracy, and injecting false answers at 3x true-answer frequency leaves accuracy unchanged (83.3%->83.3%), falsifying a frequency-based extraction account. These results establish that answer extraction operates on a sparse, order-insensitive, and structurally robust informational substrate, opening paths toward parallelized and token-efficient reasoning generation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models

Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application to generative autoregressive models remains theoretically fragmented. Existing approaches typically rely on distinct heuristics, such as teacher forcing with pseudo labels or policy-gradient-based reinforcement learning, without a unified mathematical foundation. In this work, we resolve this discrepancy by deriving a rigorous formulation of EM tailored to autoregressive models. We show that the exact objective naturally decomposes into a token-level policy gradient loss and a token-level entropy loss, and we reinterpret prior methods as partial realizations of this unified formulation. Using Whisper ASR as a testbed, we demonstrate that our approach consistently improves performance across more than 20 diverse domains, including acoustic noise, accents, and multilingual settings.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation

Objective metrics for emotional expressiveness are vital for speech generation, particularly in expressive synthesis and voice conversion requiring emotional prosody transfer. To quantify this, the field widely relies on emotion similarity between reference and generated samples. This approach computes cosine similarity of embeddings from encoders like emotion2vec, assuming they capture affective cues despite linguistic and speaker variations. We challenge this assumption through controlled adversarial tasks and human alignment tests. Despite high classification accuracy, these latent spaces are unsuitable for zero-shot similarity evaluation. Representational limitations cause linguistic and speaker interference to overshadow emotional features, degrading discriminative ability. Consequently, the metric misaligns with human perception. This acoustic vulnerability reveals it rewards acoustic mimicry over genuine emotional synthesis.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models

Recent audio-aware large language models (ALLMs) have demonstrated strong capabilities across diverse audio understanding and reasoning tasks, but they still frequently produce hallucinated or overly confident outputs. While uncertainty estimation has been extensively studied in text-only LLMs, it remains largely unexplored for ALLMs, where audio-conditioned generation introduces additional challenges such as perceptual ambiguity and cross-modal grounding. In this work, we present the first systematic empirical study of uncertainty estimation in ALLMs. We benchmark five representative methods, including predictive entropy, length-normalized entropy, semantic entropy, discrete semantic entropy, and P(True), across multiple models and diverse evaluation settings spanning general audio understanding, reasoning, hallucination detection, and unanswerable question answering. Our results reveal two key findings. First, semantic-level and verification-based methods consistently outperform token-level baselines on general audio reasoning benchmarks. Second, on trustworthiness-oriented benchmarks, the relative effectiveness of uncertainty methods becomes notably more model- and benchmark-dependent, indicating that conclusions drawn from general reasoning settings do not straightforwardly transfer to hallucination and unanswerable-question scenarios. We further explore uncertainty-based adaptive inference as a potential downstream application. We hope this study provides a foundation for future research on reliable, uncertainty-aware audio-language systems.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

Examining Forgetting in Continual Pre-training of Aligned Large Language Models

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common practice involves continual pre-training on previously fine-tuned models. However, this can lead to catastrophic forgetting. In our work, we investigate the phenomenon of forgetting that occurs during continual pre-training on an existing fine-tuned LLM. We evaluate the impact of continuous pre-training on the fine-tuned LLM across various dimensions, including output format, knowledge, and reliability. Experiment results highlight the non-trivial challenge of addressing catastrophic forgetting during continual pre-training, especially the repetition issue.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In real-world scenarios, prior to input into an LLM, an automated speech recognition (ASR) system generates an output transcript hypothesis, where inherent errors can degrade subsequent SLU tasks. Here we introduce a method that utilizes the ASR system's lattice output instead of relying solely on the top hypothesis, aiming to encapsulate speech ambiguities and enhance SLU outcomes. Our in-context learning experiments, covering spoken question answering and intent classification, underline the LLM's resilience to noisy speech transcripts with the help of word confusion networks from lattices, bridging the SLU performance gap between using the top ASR hypothesis and an oracle upper bound. Additionally, we delve into the LLM's robustness to varying ASR performance conditions and scrutinize the aspects of in-context learning which prove the most influential.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models

Self-supervised learning (SSL) is a powerful technique for learning representations from unlabeled data. Transformer based models such as HuBERT, which consist a feature extractor and transformer layers, are leading the field in the speech domain. SSL models are fine-tuned on a wide range of downstream tasks, which involves re-training the majority of the model for each task. Previous studies have introduced applying adapters, which are small lightweight modules commonly used in Natural Language Processing (NLP) to adapt pre-trained models to new tasks. However, such efficient tuning techniques only provide adaptation at the transformer layer, but failed to perform adaptation at the feature extractor. In this paper, we propose CHAPTER, an efficient tuning method specifically designed for SSL speech model, by applying CNN adapters at the feature extractor. Using this method, we can only fine-tune fewer than 5% of parameters per task compared to fully fine-tuning and achieve better and more stable performance. We empirically found that adding CNN adapters to the feature extractor can help the adaptation on emotion and speaker tasks. For instance, the accuracy of SID is improved from 87.71 to 91.56, and the accuracy of ER is improved by 5%.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision

This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, on three code-switched corpora. We found that self-supervised models can achieve performances close to the supervised model, indicating the effectiveness of multilingual self-supervised pre-training. We also observed that these models still have room for improvement as they kept making similar mistakes and had unsatisfactory performances on modeling intra-sentential code-switching. In addition, the validity of several variants of Whisper was explored, and we concluded that they remained effective in a code-switching scenario, and similar techniques for self-supervised models are worth studying to boost the performance of code-switched tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Adversarial Sample Detection for Speaker Verification by Neural Vocoders

Automatic speaker verification (ASV), one of the most important technology for biometric identification, has been widely adopted in security-critical applications. However, ASV is seriously vulnerable to recently emerged adversarial attacks, yet effective countermeasures against them are limited. In this paper, we adopt neural vocoders to spot adversarial samples for ASV. We use the neural vocoder to re-synthesize audio and find that the difference between the ASV scores for the original and re-synthesized audio is a good indicator for discrimination between genuine and adversarial samples. This effort is, to the best of our knowledge, among the first to pursue such a technical direction for detecting time-domain adversarial samples for ASV, and hence there is a lack of established baselines for comparison. Consequently, we implement the Griffin-Lim algorithm as the detection baseline. The proposed approach achieves effective detection performance that outperforms the baselines in all the settings. We also show that the neural vocoder adopted in the detection framework is dataset-independent. Our codes will be made open-source for future works to do fair comparison.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Analyzing the Robustness of Unsupervised Speech Recognition

Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with Generative Adversarial Network (GAN) training, but the robustness of the unsupervised ASR framework is unknown. In this work, we further analyze the training robustness of unsupervised ASR on the domain mismatch scenarios in which the domains of unpaired speech and text are different. Three domain mismatch scenarios include: (1) using speech and text from different datasets, (2) utilizing noisy/spontaneous speech, and (3) adjusting the amount of speech and text data. We also quantify the degree of the domain mismatch by calculating the JS-divergence of phoneme n-gram between the transcription of speech and text. This metric correlates with the performance highly. Experimental results show that domain mismatch leads to inferior performance, but a self-supervised model pre-trained on the targeted speech domain can extract better representation to alleviate the performance drop.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Anticipation-Free Training for Simultaneous Machine Translation

Simultaneous machine translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. It is difficult due to limited context and word order difference between languages. Existing methods increase latency or introduce adaptive read-write policies for SimulMT models to handle local reordering and improve translation quality. However, the long-distance reordering would make the SimulMT models learn translation mistakenly. Specifically, the model may be forced to predict target tokens when the corresponding source tokens have not been read. This leads to aggressive anticipation during inference, resulting in the hallucination phenomenon. To mitigate this problem, we propose a new framework that decompose the translation process into the monotonic translation step and the reordering step, and we model the latter by the auxiliary sorting network (ASN). The ASN rearranges the hidden states to match the order in the target language, so that the SimulMT model could learn to translate more reasonably. The entire model is optimized end-to-end and does not rely on external aligners or data. During inference, ASN is removed to achieve streaming. Experiments show the proposed framework could outperform previous methods with less latency.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Characterizing the adversarial vulnerability of speech self-supervised learning

A leaderboard named Speech processing Universal PERformance Benchmark (SUPERB), which aims at benchmarking the performance of a shared self-supervised learning (SSL) speech model across various downstream speech tasks with minimal modification of architectures and small amount of data, has fueled the research for speech representation learning. The SUPERB demonstrates speech SSL upstream models improve the performance of various downstream tasks through just minimal adaptation. As the paradigm of the self-supervised learning upstream model followed by downstream tasks arouses more attention in the speech community, characterizing the adversarial robustness of such paradigm is of high priority. In this paper, we make the first attempt to investigate the adversarial vulnerability of such paradigm under the attacks from both zero-knowledge adversaries and limited-knowledge adversaries. The experimental results illustrate that the paradigm proposed by SUPERB is seriously vulnerable to limited-knowledge adversaries, and the attacks generated by zero-knowledge adversaries are with transferability. The XAB test verifies the imperceptibility of crafted adversarial attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores

Mean opinion score (MOS) is a typical subjective evaluation metric for speech synthesis systems. Since collecting MOS is time-consuming, it would be desirable if there are accurate MOS prediction models for automatic evaluation. In this work, we propose DDOS, a novel MOS prediction model. DDOS utilizes domain adaptive pre-training to further pre-train self-supervised learning models on synthetic speech. And a proposed module is added to model the opinion score distribution of each utterance. With the proposed components, DDOS outperforms previous works on BVCC dataset. And the zero shot transfer result on BC2019 dataset is significantly improved. DDOS also wins second place in Interspeech 2022 VoiceMOS challenge in terms of system-level score.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT

Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success of these methods, they require large memory and high pre-training costs, making them inaccessible for researchers in academia and small companies. Therefore, this paper introduces DistilHuBERT, a novel multi-task learning framework to distill hidden representations from a HuBERT model directly. This method reduces HuBERT's size by 75% and 73% faster while retaining most performance in ten different tasks. Moreover, DistilHuBERT required little training time and data, opening the possibilities of pre-training personal and on-device SSL models for speech.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Don't speak too fast: The impact of data bias on self-supervised speech models

Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR. However, how pre-training data affects S3Ms' downstream behavior remains an unexplored issue. In this paper, we study how pre-training data affects S3Ms by pre-training models on biased datasets targeting different factors of speech, including gender, content, and prosody, and evaluate these pre-trained S3Ms on selected downstream tasks in SUPERB Benchmark. Our experiments show that S3Ms have tolerance toward gender bias. Moreover, we find that the content of speech has little impact on the performance of S3Ms across downstream tasks, but S3Ms do show a preference toward a slower speech rate.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering

Spoken Question Answering (SQA) is to find the answer from a spoken document given a question, which is crucial for personal assistants when replying to the queries from the users. Existing SQA methods all rely on Automatic Speech Recognition (ASR) transcripts. Not only does ASR need to be trained with massive annotated data that are time and cost-prohibitive to collect for low-resourced languages, but more importantly, very often the answers to the questions include name entities or out-of-vocabulary words that cannot be recognized correctly. Also, ASR aims to minimize recognition errors equally over all words, including many function words irrelevant to the SQA task. Therefore, SQA without ASR transcripts (textless) is always highly desired, although known to be very difficult. This work proposes Discrete Spoken Unit Adaptive Learning (DUAL), leveraging unlabeled data for pre-training and fine-tuned by the SQA downstream task. The time intervals of spoken answers can be directly predicted from spoken documents. We also release a new SQA benchmark corpus, NMSQA, for data with more realistic scenarios. We empirically showed that DUAL yields results comparable to those obtained by cascading ASR and text QA model and robust to real-world data. Our code and model will be open-sourced.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding

This paper studies a transferable phoneme embedding framework that aims to deal with the cross-lingual text-to-speech (TTS) problem under the few-shot setting. Transfer learning is a common approach when it comes to few-shot learning since training from scratch on few-shot training data is bound to overfit. Still, we find that the naive transfer learning approach fails to adapt to unseen languages under extremely few-shot settings, where less than 8 minutes of data is provided. We deal with the problem by proposing a framework that consists of a phoneme-based TTS model and a codebook module to project phonemes from different languages into a learned latent space. Furthermore, by utilizing phoneme-level averaged self-supervised learned features, we effectively improve the quality of synthesized speeches. Experiments show that using 4 utterances, which is about 30 seconds of data, is enough to synthesize intelligible speech when adapting to an unseen language using our framework.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Improving the transferability of speech separation by meta-learning

Speech separation aims to separate multiple speech sources from a speech mixture. Although speech separation is well-solved on some existing English speech separation benchmarks, it is worthy of more investigation on the generalizability of speech separation models on the accents or languages unseen during training. This paper adopts meta-learning based methods to improve the transferability of speech separation models. With the meta-learning based methods, we discovered that only using speech data with one accent, the native English accent, as our training data, the models still can be adapted to new unseen accents on the Speech Accent Archive. We compared the results with a human-rated native-likeness of accents, showing that the transferability of MAML methods has less relation to the similarity of data between the training and testing phase compared to the typical transfer learning methods. Furthermore, we found that models can deal with different language data from the CommonVoice corpus during the testing phase. Most of all, the MAML methods outperform typical transfer learning methods when it comes to new accents, new speakers, new languages, and noisy environments.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability

This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify pre-trained models' transferability, we test the pre-trained models on text classification tasks with meanings of tokens mismatches, and real-world non-text token sequence classification data, including amino acid, DNA, and music. We find that even on non-text data, the models pre-trained on text converge faster, perform better than the randomly initialized models, and only slightly worse than the models using task-specific knowledge. We also find that the representations of the text and non-text pre-trained models share non-trivial similarities.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Network

ASR has been shown to achieve great performance recently. However, most of them rely on massive paired data, which is not feasible for low-resource languages worldwide. This paper investigates how to learn directly from unpaired phone sequences and speech utterances. We design a two-stage iterative framework. GAN training is adopted in the first stage to find the mapping relationship between unpaired speech and phone sequence. In the second stage, another HMM model is introduced to train from the generator's output, which boosts the performance and provides a better segmentation for the next iteration. In the experiment, we first investigate different choices of model designs. Then we compare the framework to different types of baselines: (i) supervised methods (ii) acoustic unit discovery based methods (iii) methods learning from unpaired data. Our framework performs consistently better than all acoustic unit discovery methods and previous methods learning from unpaired data based on the TIMIT dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition

Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data distributions. Test-time Adaptation (TTA), previously explored in the computer vision area, aims to adapt the model trained on source domains to yield better predictions for test samples, often out-of-domain, without accessing the source data. Here, we propose the Single-Utterance Test-time Adaptation (SUTA) framework for ASR, which is the first TTA study on ASR to our best knowledge. The single-utterance TTA is a more realistic setting that does not assume test data are sampled from identical distribution and does not delay on-demand inference due to pre-collection for the batch of adaptation data. SUTA consists of unsupervised objectives with an efficient adaptation strategy. Empirical results demonstrate that SUTA effectively improves the performance of the source ASR model evaluated on multiple out-of-domain target corpora and in-domain test samples.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Membership Inference Attacks Against Self-supervised Speech Models

Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention. SSL models pre-trained on a huge amount of unlabeled audio can generate general-purpose representations that benefit a wide variety of speech processing tasks. Despite their ubiquitous deployment, however, the potential privacy risks of these models have not been well investigated. In this paper, we present the first privacy analysis on several SSL speech models using Membership Inference Attacks (MIA) under black-box access. The experiment results show that these pre-trained models are vulnerable to MIA and prone to membership information leakage with high Area Under the Curve (AUC) in both utterance-level and speaker-level. Furthermore, we also conduct several ablation studies to understand the factors that contribute to the success of MIA.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Meta Learning for Natural Language Processing: A Survey

Deep learning has been the mainstream technique in natural language processing (NLP) area. However, the techniques require many labeled data and are less generalizable across domains. Meta-learning is an arising field in machine learning studying approaches to learn better learning algorithms. Approaches aim at improving algorithms in various aspects, including data efficiency and generalizability. Efficacy of approaches has been shown in many NLP tasks, but there is no systematic survey of these approaches in NLP, which hinders more researchers from joining the field. Our goal with this survey paper is to offer researchers pointers to relevant meta-learning works in NLP and attract more attention from the NLP community to drive future innovation. This paper first introduces the general concepts of meta-learning and the common approaches. Then we summarize task construction settings and application of meta-learning for various NLP problems and review the development of meta-learning in NLP community.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech

Personalizing a speech synthesis system is a highly desired application, where the system can generate speech with the user's voice with rare enrolled recordings. There are two main approaches to build such a system in recent works: speaker adaptation and speaker encoding. On the one hand, speaker adaptation methods fine-tune a trained multi-speaker text-to-speech (TTS) model with few enrolled samples. However, they require at least thousands of fine-tuning steps for high-quality adaptation, making it hard to apply on devices. On the other hand, speaker encoding methods encode enrollment utterances into a speaker embedding. The trained TTS model can synthesize the user's speech conditioned on the corresponding speaker embedding. Nevertheless, the speaker encoder suffers from the generalization gap between the seen and unseen speakers. In this paper, we propose applying a meta-learning algorithm to the speaker adaptation method. More specifically, we use Model Agnostic Meta-Learning (MAML) as the training algorithm of a multi-speaker TTS model, which aims to find a great meta-initialization to adapt the model to any few-shot speaker adaptation tasks quickly. Therefore, we can also adapt the meta-trained TTS model to unseen speakers efficiently. Our experiments compare the proposed method (Meta-TTS) with two baselines: a speaker adaptation method baseline and a speaker encoding method baseline. The evaluation results show that Meta-TTS can synthesize high speaker-similarity speech from few enrollment samples with fewer adaptation steps than the speaker adaptation baseline and outperforms the speaker encoding baseline under the same training scheme. When the speaker encoder of the baseline is pre-trained with extra 8371 speakers of data, Meta-TTS can still outperform the baseline on LibriTTS dataset and achieve comparable results on VCTK dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what specific traits in the pre-training data, other than the semantics, make a pre-trained LM superior to their counterparts trained from scratch on downstream tasks. We propose to use artificially constructed datasets as the pre-training data to exclude the effect of semantics, and further control what characteristics the pre-training corpora have. By fine-tuning the pre-trained models on GLUE benchmark, we can learn how beneficial it is to transfer the knowledge from the model trained on the dataset possessing that specific trait. We define and discuss three different characteristics in the artificial dataset: 1) matching the token's uni-gram or bi-gram distribution between pre-training and downstream fine-tuning, 2) the presence of the explicit dependencies among the tokens in a sequence, 3) the length of the implicit dependencies among the tokens in a sequence. Our experiments show that the explicit dependencies in the sequences of the pre-training data are critical to the downstream performance. Our results also reveal that models achieve better downstream performance when pre-trained on a dataset with a longer range of implicit dependencies. Based on our analysis, we find that models pre-trained with artificial datasets are prone to learn spurious correlation in downstream tasks. Our work reveals that even if the LMs are not pre-trained on natural language, they still gain transferability on certain human language downstream tasks once the LMs learn to model the token dependencies in the sequences. This result helps us understand the exceptional transferability of pre-trained LMs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Partially Fake Audio Detection by Self-attention-based Fake Span Discovery

The past few years have witnessed the significant advances of speech synthesis and voice conversion technologies. However, such technologies can undermine the robustness of broadly implemented biometric identification models and can be harnessed by in-the-wild attackers for illegal uses. The ASVspoof challenge mainly focuses on synthesized audios by advanced speech synthesis and voice conversion models, and replay attacks. Recently, the first Audio Deep Synthesis Detection challenge (ADD 2022) extends the attack scenarios into more aspects. Also ADD 2022 is the first challenge to propose the partially fake audio detection task. Such brand new attacks are dangerous and how to tackle such attacks remains an open question. Thus, we propose a novel framework by introducing the question-answering (fake span discovery) strategy with the self-attention mechanism to detect partially fake audios. The proposed fake span detection module tasks the anti-spoofing model to predict the start and end positions of the fake clip within the partially fake audio, address the model's attention into discovering the fake spans rather than other shortcuts with less generalization, and finally equips the model with the discrimination capacity between real and partially fake audios. Our submission ranked second in the partially fake audio detection track of ADD 2022.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Re-Examining Human Annotations for Interpretable NLP

Explanation methods in Interpretable NLP often explain the model's decision by extracting evidence (rationale) from the input texts supporting the decision. Benchmark datasets for rationales have been released to evaluate how good the rationale is. The ground truth rationales in these datasets are often human annotations obtained via crowd-sourced websites. Valuable as these datasets are, the details on how those human annotations are obtained are often not clearly specified. We conduct comprehensive controlled experiments using crowd-sourced websites on two widely used datasets in Interpretable NLP to understand how those unsaid details can affect the annotation results. Specifically, we compare the annotation results obtained from recruiting workers satisfying different levels of qualification. We also provide high-quality workers with different instructions for completing the same underlying tasks. Our results reveal that the annotation quality is highly subject to the workers' qualification, and workers can be guided to provide certain annotations by the instructions. We further show that specific explanation methods perform better when evaluated using the ground truth rationales obtained by particular instructions. Based on these observations, we highlight the importance of providing complete details of the annotation process and call for careful interpretation of any experiment results obtained using those annotations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information

Self-Supervised Learning (SSL) has made great strides recently. SSL speech models achieve decent performance on a wide range of downstream tasks, suggesting that they extract different aspects of information from speech. However, how SSL models store various information in hidden representations without interfering is still poorly understood. Taking the recently successful SSL model, HuBERT, as an example, we explore how the SSL model processes and stores speaker information in the representation. We found that HuBERT stores speaker information in representations whose positions correspond to silences in a waveform. There are several pieces of evidence. (1) We find that the utterances with more silent parts in the waveforms have better Speaker Identification (SID) accuracy. (2) If we use the whole utterances for SID, the silence part always contributes more to the SID task. (3) If we only use the representation of a part of the utterance for SID, the silenced part has higher accuracy than the other parts. Our findings not only contribute to a better understanding of SSL models but also improve performance. By simply adding silence to the original waveform, HuBERT improved its accuracy on SID by nearly 2%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks

Speech representations learned from Self-supervised learning (SSL) models can benefit various speech processing tasks. However, utilizing SSL representations usually requires fine-tuning the pre-trained models or designing task-specific downstream models and loss functions, causing much memory usage and human labor. Recently, prompting in Natural Language Processing (NLP) has been found to be an efficient technique to leverage pre-trained language models (LMs). Specifically, prompt tuning optimizes a limited number of task-specific parameters with a fixed pre-trained model; as a result, only a small set of parameters is needed to be stored for each task. Prompt tuning improves computation and memory efficiency by leveraging the pre-trained LM's prediction ability. Nevertheless, such a paradigm is little studied in the speech community. We report in this paper the first exploration of the prompt tuning paradigm for speech processing tasks based on Generative Spoken Language Model (GSLM). Experiment results show that the prompt tuning technique achieves competitive performance in speech classification tasks with fewer trainable parameters than fine-tuning specialized downstream models. We further study the technique in challenging sequence generation tasks. Prompt tuning also demonstrates its potential, while the limitation and possible research directions are discussed in this paper. The source code is available on https://github.com/ga642381/SpeechPrompt.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Spoofing-Aware Speaker Verification by Multi-Level Fusion

Recently, many novel techniques have been introduced to deal with spoofing attacks, and achieve promising countermeasure (CM) performances. However, these works only take the stand-alone CM models into account. Nowadays, a spoofing aware speaker verification (SASV) challenge which aims to facilitate the research of integrated CM and ASV models, arguing that jointly optimizing CM and ASV models will lead to better performance, is taking place. In this paper, we propose a novel multi-model and multi-level fusion strategy to tackle the SASV task. Compared with purely scoring fusion and embedding fusion methods, this framework first utilizes embeddings from CM models, propagating CM embeddings into a CM block to obtain a CM score. In the second-level fusion, the CM score and ASV scores directly from ASV systems will be concatenated into a prediction block for the final decision. As a result, the best single fusion system has achieved the SASV-EER of 0.97% on the evaluation set. Then by ensembling the top-5 fusion systems, the final SASV-EER reached 0.89%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Structured Prompt Tuning

We propose structured prompt tuning, a simple and effective method to improve prompt tuning. Instead of prepending a sequence of tunable embeddings to the input, we generate the soft prompt embeddings through a hypernetwork. Our approach subsumes the standard prompt tuning, allows more flexibility in model design and can be applied to both single-task and multi-task training settings. Empirically, structured prompt tuning shows a gain of +1.2$~1.5 points on the GLUE benchmark and is less sensitive to the change of learning rate, compared to standard prompt tuning.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities

Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabilities of pre-trained models by increasing task diversity and difficulty over SUPERB. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain and quality across different types of tasks. It entails freezing pre-trained model parameters, only using simple task-specific trainable heads. The goal is to be inclusive of all researchers, and encourage efficient use of computational resources. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion

Recent years have witnessed the extraordinary development of automatic speaker verification (ASV). However, previous works show that state-of-the-art ASV models are seriously vulnerable to voice spoofing attacks, and the recently proposed high-performance spoofing countermeasure (CM) models only focus solely on the standalone anti-spoofing tasks, and ignore the subsequent speaker verification process. How to integrate the CM and ASV together remains an open question. A spoofing aware speaker verification (SASV) challenge has recently taken place with the argument that better performance can be delivered when both CM and ASV subsystems are optimized jointly. Under the challenge's scenario, the integrated systems proposed by the participants are required to reject both impostor speakers and spoofing attacks from target speakers, which intuitively and effectively matches the expectation of a reliable, spoofing-robust ASV system. This work focuses on fusion-based SASV solutions and proposes a multi-model fusion framework to leverage the power of multiple state-of-the-art ASV and CM models. The proposed framework vastly improves the SASV-EER from 8.75% to 1.17\%, which is 86% relative improvement compared to the best baseline system in the SASV challenge.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Toward Degradation-Robust Voice Conversion

Any-to-any voice conversion technologies convert the vocal timbre of an utterance to any speaker even unseen during training. Although there have been several state-of-the-art any-to-any voice conversion models, they were all based on clean utterances to convert successfully. However, in real-world scenarios, it is difficult to collect clean utterances of a speaker, and they are usually degraded by noises or reverberations. It thus becomes highly desired to understand how these degradations affect voice conversion and build a degradation-robust model. We report in this paper the first comprehensive study on the degradation robustness of any-to-any voice conversion. We show that the performance of state-of-the-art models nowadays was severely hampered given degraded utterances. To this end, we then propose speech enhancement concatenation and denoising training to improve the robustness. In addition to common degradations, we also consider adversarial noises, which alter the model output significantly yet are human-imperceptible. It was shown that both concatenations with off-the-shelf speech enhancement models and denoising training on voice conversion models could improve the robustness, while each of them had pros and cons.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Understanding, Detecting, and Separating Out-of-Distribution Samples and Adversarial Samples in Text Classification

In this paper, we study the differences and commonalities between statistically out-of-distribution (OOD) samples and adversarial (Adv) samples, both of which hurting a text classification model's performance. We conduct analyses to compare the two types of anomalies (OOD and Adv samples) with the in-distribution (ID) ones from three aspects: the input features, the hidden representations in each layer of the model, and the output probability distributions of the classifier. We find that OOD samples expose their aberration starting from the first layer, while the abnormalities of Adv samples do not emerge until the deeper layers of the model. We also illustrate that the models' output probabilities for Adv samples tend to be more unconfident. Based on our observations, we propose a simple method to separate ID, OOD, and Adv samples using the hidden representations and output probabilities of the model. On multiple combinations of ID, OOD datasets, and Adv attacks, our proposed method shows exceptional results on distinguishing ID, OOD, and Adv samples.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Adversarial defense for automatic speaker verification by cascaded self-supervised learning models

Automatic speaker verification (ASV) is one of the core technologies in biometric identification. With the ubiquitous usage of ASV systems in safety-critical applications, more and more malicious attackers attempt to launch adversarial attacks at ASV systems. In the midst of the arms race between attack and defense in ASV, how to effectively improve the robustness of ASV against adversarial attacks remains an open question. We note that the self-supervised learning models possess the ability to mitigate superficial perturbations in the input after pretraining. Hence, with the goal of effective defense in ASV against adversarial attacks, we propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks in scenarios where attackers may either be aware or unaware of the self-supervised learning models.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT

Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box. A variety of previous works have tried to lift the veil of BERT and understand each layer's functionality. In this paper, we found that surprisingly the output layer of BERT can reconstruct the input sentence by directly taking each layer of BERT as input, even though the output layer has never seen the input other than the final hidden layer. This fact remains true across a wide variety of BERT-based models, even when some layers are duplicated. Based on this observation, we propose a quite simple method to boost the performance of BERT. By duplicating some layers in the BERT-based models to make it deeper (no extra training required in this step), they obtain better performance in the downstream tasks after fine-tuning.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Study of Cross-Lingual Ability and Language-specific Information in Multilingual BERT

Recently, multilingual BERT works remarkably well on cross-lingual transfer tasks, superior to static non-contextualized word embeddings. In this work, we provide an in-depth experimental study to supplement the existing literature of cross-lingual ability. We compare the cross-lingual ability of non-contextualized and contextualized representation model with the same data. We found that datasize and context window size are crucial factors to the transferability. We also observe the language-specific information in multilingual BERT. By manipulating the latent representations, we can control the output languages of multilingual BERT, and achieve unsupervised token translation. We further show that based on the observation, there is a computationally cheap but effective approach to improve the cross-lingual ability of multilingual BERT.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation

In previous works, only parameter weights of ASR models are optimized under fixed-topology architecture. However, the design of successful model architecture has always relied on human experience and intuition. Besides, many hyperparameters related to model architecture need to be manually tuned. Therefore in this paper, we propose an ASR approach with efficient gradient-based architecture search, DARTS-ASR. In order to examine the generalizability of DARTS-ASR, we apply our approach not only on many languages to perform monolingual ASR, but also on a multilingual ASR setting. Following previous works, we conducted experiments on a multilingual dataset, IARPA BABEL. The experiment results show that our approach outperformed the baseline fixed-topology architecture by 10.2% and 10.0% relative reduction on character error rates under monolingual and multilingual ASR settings respectively. Furthermore, we perform some analysis on the searched architectures by DARTS-ASR.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Defense against adversarial attacks on spoofing countermeasures of ASV

Various forefront countermeasure methods for automatic speaker verification (ASV) with considerable performance in anti-spoofing are proposed in the ASVspoof 2019 challenge. However, previous work has shown that countermeasure models are vulnerable to adversarial examples indistinguishable from natural data. A good countermeasure model should not only be robust against spoofing audio, including synthetic, converted, and replayed audios; but counteract deliberately generated examples by malicious adversaries. In this work, we introduce a passive defense method, spatial smoothing, and a proactive defense method, adversarial training, to mitigate the vulnerability of ASV spoofing countermeasure models against adversarial examples. This paper is among the first to use defense methods to improve the robustness of ASV spoofing countermeasure models under adversarial attacks. The experimental results show that these two defense methods positively help spoofing countermeasure models counter adversarial examples.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Investigation of Sentiment Controllable Chatbot

Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. In this paper, we investigate four models to scale or adjust the sentiment of the chatbot response: a persona-based model, reinforcement learning, a plug and play model, and CycleGAN, all based on the seq2seq model. We also develop machine-evaluated metrics to estimate whether the responses are reasonable given the input. These metrics, together with human evaluation, are used to analyze the performance of the four models in terms of different aspects; reinforcement learning and CycleGAN are shown to be very attractive.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification

Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the difficulty of training, learning discrete representations for unlabeled textual data has not been widely explored. This work proposes TIGAN that learns to encode texts into two disentangled representations, including a discrete code and a continuous noise, where the discrete code represents interpretable topics, and the noise controls the variance within the topics. The discrete code learned by TIGAN can be used for unsupervised text classification. Compared to other unsupervised baselines, the proposed TIGAN achieves superior performance on six different corpora. Also, the performance is on par with a recently proposed weakly-supervised text classification method. The extracted topical words for representing latent topics show that TIGAN learns coherent and highly interpretable topics.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders

We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and predicting information about future frames. Whereas Mockingjay is designed to predict the current frame through jointly conditioning on both past and future contexts. The Mockingjay representation improves performance for a wide range of downstream tasks, including phoneme classification, speaker recognition, and sentiment classification on spoken content, while outperforming other approaches. Mockingjay is empirically powerful and can be fine-tuned with downstream models, with only 2 epochs we further improve performance dramatically. In a low resource setting with only 0.1% of labeled data, we outperform the result of Mel-features that uses all 100% labeled data.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

SADDEL: Joint Speech Separation and Denoising Model based on Multitask Learning

Speech data collected in real-world scenarios often encounters two issues. First, multiple sources may exist simultaneously, and the number of sources may vary with time. Second, the existence of background noise in recording is inevitable. To handle the first issue, we refer to speech separation approaches, that separate speech from an unknown number of speakers. To address the second issue, we refer to speech denoising approaches, which remove noise components and retrieve pure speech signals. Numerous deep learning based methods for speech separation and denoising have been proposed that show promising results. However, few works attempt to address the issues simultaneously, despite speech separation and denoising tasks having similar nature. In this study, we propose a joint speech separation and denoising framework based on the multitask learning criterion to tackle the two issues simultaneously. The experimental results show that the proposed framework not only performs well on both speech separation and denoising tasks, but also outperforms related methods in most conditions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes prevent many institutes from building multi-speaker TTS systems of great performance. In this work, we propose a semi-supervised learning approach for multi-speaker TTS. A multi-speaker TTS model can learn from the untranscribed audio via the proposed encoder-decoder framework with discrete speech representation. The experiment results demonstrate that with only an hour of paired speech data, no matter the paired data is from multiple speakers or a single speaker, the proposed model can generate intelligible speech in different voices. We found the model can benefit from the proposed semi-supervised learning approach even when part of the unpaired speech data is noisy. In addition, our analysis reveals that different speaker characteristics of the paired data have an impact on the effectiveness of semi-supervised TTS.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding

In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the cosine similarity between a transformed decoder feature and the target word embedding. Based on the regularized decoder, we further proposed the fused decoding mechanism. This allows the decoder to consider the semantic consistency during decoding by absorbing the information carried by the transformed decoder feature, which is learned to be close to the target word embedding. Initial results on LibriSpeech demonstrated that pre-trained word embedding can significantly lower ASR recognition error with a negligible cost, and the choice of word embedding algorithms among Skip-gram, CBOW and BERT is important.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering

While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning from the very successful BERT model for various text processing tasks, here we proposed an audio-and-text jointly learned SpeechBERT model. This model outperformed the conventional approach of cascading ASR with the following text question answering (TQA) model on datasets including ASR errors in answer spans, because the end-to-end model was shown to be able to extract information out of audio data before ASR produced errors. When ensembling the proposed end-to-end model with the cascade architecture, even better performance was achieved. In addition to the potential of end-to-end SQA, the SpeechBERT can also be considered for many other spoken language understanding tasks just as BERT for many text processing tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Robust Neural Vocoding for Speech Generation: A Survey

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocoders trained on real data often degrade in voice quality for unseen scenarios. In this paper, we train four common neural vocoders, including WaveNet, WaveRNN, FFTNet, Parallel WaveGAN alternately on five different datasets. To study the robustness of neural vocoders, we evaluate the models using acoustic features from seen/unseen speakers, seen/unseen languages, a text-to-speech model, and a voice conversion model. We found out that the speaker variety is much more important for achieving a universal vocoder than the language. Through our experiments, we show that WaveNet and WaveRNN are more suitable for text-to-speech models, while Parallel WaveGAN is more suitable for voice conversion applications. Great amount of subjective MOS results in naturalness for all vocoders are presented for future studies.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning

In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is achieved by proper temporal segmentation to make the representations phoneme-synchronized, and proper phonetic clustering to have total number of distinct representations close to the number of phonemes. Mapping between the distinct representations and phonemes is learned from a small amount of annotated paired data. Preliminary experiments on LJSpeech demonstrated the learned representations for vowels have relative locations in latent space in good parallel to that shown in the IPA vowel chart defined by linguistics experts. With less than 20 minutes of annotated speech, our method outperformed existing methods on phoneme recognition and is able to synthesize intelligible speech that beats our baseline model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Training a code-switching language model with monolingual data

A lack of code-switching data complicates the training of code-switching (CS) language models. We propose an approach to train such CS language models on monolingual data only. By constraining and normalizing the output projection matrix in RNN-based language models, we bring embeddings of different languages closer to each other. Numerical and visualization results show that the proposed approaches remarkably improve the performance of CS language models trained on monolingual data. The proposed approaches are comparable or even better than training CS language models with artificially generated CS data. We additionally use unsupervised bilingual word translation to analyze whether semantically equivalent words in different languages are mapped together.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Understanding Self-Attention of Self-Supervised Audio Transformers

Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been widely explored yet. In this work, we present multiple strategies for the analysis of attention mechanisms in SAT. We categorize attentions into explainable categories, where we discover each category possesses its own unique functionality. We provide a visualization tool for understanding multi-head self-attention, importance ranking strategies for identifying critical attention, and attention refinement techniques to improve model performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture

Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting. Auto-encoder-based VC methods disentangle the speaker and the content in input speech without given the speaker's identity, so these methods can further generalize to unseen speakers. The disentangle capability is achieved by vector quantization (VQ), adversarial training, or instance normalization (IN). However, the imperfect disentanglement may harm the quality of output speech. In this work, to further improve audio quality, we use the U-Net architecture within an auto-encoder-based VC system. We find that to leverage the U-Net architecture, a strong information bottleneck is necessary. The VQ-based method, which quantizes the latent vectors, can serve the purpose. The objective and the subjective evaluations show that the proposed method performs well in both audio naturalness and speaker similarity.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

WG-WaveNet: Real-Time High-Fidelity Speech Synthesis without GPU

In this paper, we propose WG-WaveNet, a fast, lightweight, and high-quality waveform generation model. WG-WaveNet is composed of a compact flow-based model and a post-filter. The two components are jointly trained by maximizing the likelihood of the training data and optimizing loss functions on the frequency domains. As we design a flow-based model that is heavily compressed, the proposed model requires much less computational resources compared to other waveform generation models during both training and inference time; even though the model is highly compressed, the post-filter maintains the quality of generated waveform. Our PyTorch implementation can be trained using less than 8 GB GPU memory and generates audio samples at a rate of more than 960 kHz on an NVIDIA 1080Ti GPU. Furthermore, even if synthesizing on a CPU, we show that the proposed method is capable of generating 44.1 kHz speech waveform 1.2 times faster than real-time. Experiments also show that the quality of generated audio is comparable to those of other methods. Audio samples are publicly available online.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation

Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates the text of the source language, and the translation decoder obtains the final translations based on the output of the recognition decoder. Because whether the output of the recognition decoder has the correct semantics is more critical than its accuracy, we propose to improve the multitask ST model by utilizing word embedding as the intermediate.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion

We present an unsupervised end-to-end training scheme where we discover discrete subword units from speech without using any labels. The discrete subword units are learned under an ASR-TTS autoencoder reconstruction setting, where an ASR-Encoder is trained to discover a set of common linguistic units given a variety of speakers, and a TTS-Decoder trained to project the discovered units back to the designated speech. We propose a discrete encoding method, Multilabel-Binary Vectors (MBV), to make the ASR-TTS autoencoder differentiable. We found that the proposed encoding method offers automatic extraction of speech content from speaker style, and is sufficient to cover full linguistic content in a given language. Therefore, the TTS-Decoder can synthesize speech with the same content as the input of ASR-Encoder but with different speaker characteristics, which achieves voice conversion (VC). We further improve the quality of VC using adversarial training, where we train a TTS-Patcher that augments the output of TTS-Decoder. Objective and subjective evaluations show that the proposed approach offers strong VC results as it eliminates speaker identity while preserving content within speech. In the ZeroSpeech 2019 Challenge, we achieved outstanding performance in terms of low bitrate.

0 citations0 reviewsNo code linkedOpen access