2023-11-05 更新
Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading
Authors:Songtao Luo, Shuang Yang, Shiguang Shan, Xilin Chen
In this paper, we propose a novel method for speaker adaptation in lip reading, motivated by two observations. Firstly, a speaker’s own characteristics can always be portrayed well by his/her few facial images or even a single image with shallow networks, while the fine-grained dynamic features associated with speech content expressed by the talking face always need deep sequential networks to represent accurately. Therefore, we treat the shallow and deep layers differently for speaker adaptive lip reading. Secondly, we observe that a speaker’s unique characteristics ( e.g. prominent oral cavity and mandible) have varied effects on lip reading performance for different words and pronunciations, necessitating adaptive enhancement or suppression of the features for robust lip reading. Based on these two observations, we propose to take advantage of the speaker’s own characteristics to automatically learn separable hidden unit contributions with different targets for shallow layers and deep layers respectively. For shallow layers where features related to the speaker’s characteristics are stronger than the speech content related features, we introduce speaker-adaptive features to learn for enhancing the speech content features. For deep layers where both the speaker’s features and the speech content features are all expressed well, we introduce the speaker-adaptive features to learn for suppressing the speech content irrelevant noise for robust lip reading. Our approach consistently outperforms existing methods, as confirmed by comprehensive analysis and comparison across different settings. Besides the evaluation on the popular LRW-ID and GRID datasets, we also release a new dataset for evaluation, CAS-VSR-S68h, to further assess the performance in an extreme setting where just a few speakers are available but the speech content covers a large and diversified range.
PDF Accepted to BMVC 2023 20pages
点此查看论文截图
Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting
Authors:Zhiyu Chen, Yujie Lu, William Yang Wang
Mental illness remains one of the most critical public health issues of our time, due to the severe scarcity and accessibility limit of professionals. Psychotherapy requires high-level expertise to conduct deep, complex reasoning and analysis on the cognition modeling of the patients. In the era of Large Language Models, we believe it is the right time to develop AI assistance for computational psychotherapy. We study the task of cognitive distortion detection and propose the Diagnosis of Thought (DoT) prompting. DoT performs diagnosis on the patient’s speech via three stages: subjectivity assessment to separate the facts and the thoughts; contrastive reasoning to elicit the reasoning processes supporting and contradicting the thoughts; and schema analysis to summarize the cognition schemas. The generated diagnosis rationales through the three stages are essential for assisting the professionals. Experiments demonstrate that DoT obtains significant improvements over ChatGPT for cognitive distortion detection, while generating high-quality rationales approved by human experts.
PDF EMNLP 2023 Findings
点此查看论文截图
A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and Extraction
Authors:Kohei Saijo, Wangyou Zhang, Zhong-Qiu Wang, Shinji Watanabe, Tetsunori Kobayashi, Tetsuji Ogawa
We propose a multi-task universal speech enhancement (MUSE) model that can perform five speech enhancement (SE) tasks: dereverberation, denoising, speech separation (SS), target speaker extraction (TSE), and speaker counting. This is achieved by integrating two modules into an SE model: 1) an internal separation module that does both speaker counting and separation; and 2) a TSE module that extracts the target speech from the internal separation outputs using target speaker cues. The model is trained to perform TSE if the target speaker cue is given and SS otherwise. By training the model to remove noise and reverberation, we allow the model to tackle the five tasks mentioned above with a single model, which has not been accomplished yet. Evaluation results demonstrate that the proposed MUSE model can successfully handle multiple tasks with a single model.
PDF 6 pages, 4 figures, 2 tables, accepted by ASRU2023
点此查看论文截图
Real-time Speech Enhancement and Separation with a Unified Deep Neural Network for Single/Dual Talker Scenarios
Authors:Kashyap Patel, Anton Kovalyov, Issa Panahi
This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active speakers. Scale-invariant signal-to-distortion ratio (SI-SDR) has shown to be a highly effective training measure in time-domain speech separation. However, the SI-SDR metric is ill-defined for zero-energy target signals, which is a problem when training a speech separation model using utterances with varying numbers of talkers. Unlike existing solutions that focus on modifying the loss function to accommodate zero-energy target signals, the proposed approach circumvents this problem by training the model to extract speech on both its output channels regardless if the input is a single or dual-talker mixture. A lightweight speaker overlap detection (SOD) module is also introduced to differentiate between single and dual-talker segments in real-time. The proposed module takes advantage of the new formulation by operating directly on the separated masks, given by the separation model, instead of the original mixture, thus effectively simplifying the detection task. Experimental results show that the proposed training approach outperforms existing solutions, and the SOD module exhibits high accuracy.
PDF 6 Pages, Accepted at IEEE Asilomar
点此查看论文截图
GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding
Authors:Vibhor Agarwal, Yu Chen, Nishanth Sastry
Online conversation understanding is an important yet challenging NLP problem which has many useful applications (e.g., hate speech detection). However, online conversations typically unfold over a series of posts and replies to those posts, forming a tree structure within which individual posts may refer to semantic context from higher up the tree. Such semantic cross-referencing makes it difficult to understand a single post by itself; yet considering the entire conversation tree is not only difficult to scale but can also be misleading as a single conversation may have several distinct threads or points, not all of which are relevant to the post being considered. In this paper, we propose a Graph-based Attentive Semantic COntext Modeling (GASCOM) framework for online conversation understanding. Specifically, we design two novel algorithms that utilise both the graph structure of the online conversation as well as the semantic information from individual posts for retrieving relevant context nodes from the whole conversation. We further design a token-level multi-head graph attention mechanism to pay different attentions to different tokens from different selected context utterances for fine-grained conversation context modeling. Using this semantic conversational context, we re-examine two well-studied problems: polarity prediction and hate speech detection. Our proposed framework significantly outperforms state-of-the-art methods on both tasks, improving macro-F1 scores by 4.5% for polarity prediction and by 5% for hate speech detection. The GASCOM context weights also enhance interpretability.
PDF
点此查看论文截图
How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation
Authors:Marco Gaido, Dennis Fucci, Matteo Negri, Luisa Bentivogli
When translating from notional gender languages (e.g., English) into grammatical gender languages (e.g., Italian), the generated translation requires explicit gender assignments for various words, including those referring to the speaker. When the source sentence does not convey the speaker’s gender, speech translation (ST) models either rely on the possibly-misleading vocal traits of the speaker or default to the masculine gender, the most frequent in existing training corpora. To avoid such biased and not inclusive behaviors, the gender assignment of speaker-related expressions should be guided by externally-provided metadata about the speaker’s gender. While previous work has shown that the most effective solution is represented by separate, dedicated gender-specific models, the goal of this paper is to achieve the same results by integrating the speaker’s gender metadata into a single “multi-gender” neural ST model, easier to maintain. Our experiments demonstrate that a single multi-gender model outperforms gender-specialized ones when trained from scratch (with gender accuracy gains up to 12.9 for feminine forms), while fine-tuning from existing ST models does not lead to competitive results.
PDF To appear in CLiC-it 2023
点此查看论文截图
CL-MASR: A Continual Learning Benchmark for Multilingual ASR
Authors:Luca Della Libera, Pooneh Mousavi, Salah Zaiem, Cem Subakan, Mirco Ravanelli
Modern multilingual automatic speech recognition (ASR) systems like Whisper have made it possible to transcribe audio in multiple languages with a single model. However, current state-of-the-art ASR models are typically evaluated on individual languages or in a multi-task setting, overlooking the challenge of continually learning new languages. There is insufficient research on how to add new languages without losing valuable information from previous data. Furthermore, existing continual learning benchmarks focus mostly on vision and language tasks, leaving continual learning for multilingual ASR largely unexplored. To bridge this gap, we propose CL-MASR, a benchmark designed for studying multilingual ASR in a continual learning setting. CL-MASR provides a diverse set of continual learning methods implemented on top of large-scale pretrained ASR models, along with common metrics to assess the effectiveness of learning new languages while addressing the issue of catastrophic forgetting. To the best of our knowledge, CL-MASR is the first continual learning benchmark for the multilingual ASR task. The code is available at https://github.com/speechbrain/benchmarks.
PDF 16 pages, 5 figures, 5 tables
点此查看论文截图
Single channel speech enhancement by colored spectrograms
Authors:Sania Gul, Muhammad Salman Khan, Muhammad Fazeel
Speech enhancement concerns the processes required to remove unwanted background sounds from the target speech to improve its quality and intelligibility. In this paper, a novel approach for single-channel speech enhancement is presented, using colored spectrograms. We propose the use of a deep neural network (DNN) architecture adapted from the pix2pix generative adversarial network (GAN) and train it over colored spectrograms of speech to denoise them. After denoising, the colors of spectrograms are translated to magnitudes of short-time Fourier transform (STFT) using a shallow regression neural network. These estimated STFT magnitudes are later combined with the noisy phases to obtain an enhanced speech. The results show an improvement of almost 0.84 points in the perceptual evaluation of speech quality (PESQ) and 1% in the short-term objective intelligibility (STOI) over the unprocessed noisy data. The gain in quality and intelligibility over the unprocessed signal is almost equal to the gain achieved by the baseline methods used for comparison with the proposed model, but at a much reduced computational cost. The proposed solution offers a comparative PESQ score at almost 10 times reduced computational cost than a similar baseline model that has generated the highest PESQ score trained on grayscaled spectrograms, while it provides only a 1% deficit in STOI at 28 times reduced computational cost when compared to another baseline system based on convolutional neural network-GAN (CNN-GAN) that produces the most intelligible speech.
PDF 18 pages, 6 figures, 5 tables
点此查看论文截图
Privacy-preserving Representation Learning for Speech Understanding
Authors:Minh Tran, Mohammad Soleymani
Existing privacy-preserving speech representation learning methods target a single application domain. In this paper, we present a novel framework to anonymize utterance-level speech embeddings generated by pre-trained encoders and show its effectiveness for a range of speech classification tasks. Specifically, given the representations from a pre-trained encoder, we train a Transformer to estimate the representations for the same utterances spoken by other speakers. During inference, the extracted representations can be converted into different identities to preserve privacy. We compare the results with the voice anonymization baselines from the VoicePrivacy 2022 challenge. We evaluate our framework on speaker identification for privacy and emotion recognition, depression classification, and intent classification for utility. Our method outperforms the baselines on privacy and utility in paralinguistic tasks and achieves comparable performance for intent classification.
PDF INTERSPEECH 2023
点此查看论文截图
Dialect Adaptation and Data Augmentation for Low-Resource ASR: TalTech Systems for the MADASR 2023 Challenge
Authors:Tanel Alumäe, Jiaming Kong, Daniil Robnikov
This paper describes Tallinn University of Technology (TalTech) systems developed for the ASRU MADASR 2023 Challenge. The challenge focuses on automatic speech recognition of dialect-rich Indian languages with limited training audio and text data. TalTech participated in two tracks of the challenge: Track 1 that allowed using only the provided training data and Track 3 which allowed using additional audio data. In both tracks, we relied on wav2vec2.0 models. Our methodology diverges from the traditional procedure of finetuning pretrained wav2vec2.0 models in two key points: firstly, through the implementation of the aligned data augmentation technique to enhance the linguistic diversity of the training data, and secondly, via the application of deep prefix tuning for dialect adaptation of wav2vec2.0 models. In both tracks, our approach yielded significant improvements over the provided baselines, achieving the lowest word error rates across all participating teams.
PDF
点此查看论文截图
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Authors:Jeff Hwang, Moto Hira, Caroline Chen, Xiaohui Zhang, Zhaoheng Ni, Guangzhi Sun, Pingchuan Ma, Ruizhe Huang, Vineel Pratap, Yuekai Zhang, Anurag Kumar, Chin-Yun Yu, Chuang Zhu, Chunxi Liu, Jacob Kahn, Mirco Ravanelli, Peng Sun, Shinji Watanabe, Yangyang Shi, Yumeng Tao, Robin Scheibler, Samuele Cornell, Sean Kim, Stavros Petridis
TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing well-designed, easy-to-use, and performant PyTorch components. Its contributors routinely engage with users to understand their needs and fulfill them by developing impactful features. Here, we survey TorchAudio’s development principles and contents and highlight key features we include in its latest version (2.1): self-supervised learning pre-trained pipelines and training recipes, high-performance CTC decoders, speech recognition models and training recipes, advanced media I/O capabilities, and tools for performing forced alignment, multi-channel speech enhancement, and reference-less speech assessment. For a selection of these features, through empirical studies, we demonstrate their efficacy and show that they achieve competitive or state-of-the-art performance.
PDF
点此查看论文截图
Unified Segment-to-Segment Framework for Simultaneous Sequence Generation
Authors:Shaolei Zhang, Yang Feng
Simultaneous sequence generation is a pivotal task for real-time scenarios, such as streaming speech recognition, simultaneous machine translation and simultaneous speech translation, where the target sequence is generated while receiving the source sequence. The crux of achieving high-quality generation with low latency lies in identifying the optimal moments for generating, accomplished by learning a mapping between the source and target sequences. However, existing methods often rely on task-specific heuristics for different sequence types, limiting the model’s capacity to adaptively learn the source-target mapping and hindering the exploration of multi-task learning for various simultaneous tasks. In this paper, we propose a unified segment-to-segment framework (Seg2Seg) for simultaneous sequence generation, which learns the mapping in an adaptive and unified manner. During the process of simultaneous generation, the model alternates between waiting for a source segment and generating a target segment, making the segment serve as the natural bridge between the source and target. To accomplish this, Seg2Seg introduces a latent segment as the pivot between source to target and explores all potential source-target mappings via the proposed expectation training, thereby learning the optimal moments for generating. Experiments on multiple simultaneous generation tasks demonstrate that Seg2Seg achieves state-of-the-art performance and exhibits better generality across various tasks.
PDF Accepted at NeurIPS 2023
点此查看论文截图
Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model
Authors:Suyeon Lee, Chaeyoung Jung, Youngjoon Jang, Jaehun Kim, Joon Son Chung
The objective of this work is to extract target speaker’s voice from a mixture of voices using visual cues. Existing works on audio-visual speech separation have demonstrated their performance with promising intelligibility, but maintaining naturalness remains a challenge. To address this issue, we propose AVDiffuSS, an audio-visual speech separation model based on a diffusion mechanism known for its capability in generating natural samples. For an effective fusion of the two modalities for diffusion, we also propose a cross-attention-based feature fusion mechanism. This mechanism is specifically tailored for the speech domain to integrate the phonetic information from audio-visual correspondence in speech generation. In this way, the fusion process maintains the high temporal resolution of the features, without excessive computational requirements. We demonstrate that the proposed framework achieves state-of-the-art results on two benchmarks, including VoxCeleb2 and LRS3, producing speech with notably better naturalness.
PDF Project page with demo: https://mm.kaist.ac.kr/projects/avdiffuss/
点此查看论文截图
Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
Authors:Zexu Pan, Gordon Wichern, Yoshiki Masuyama, Francois G. Germain, Sameer Khurana, Chiori Hori, Jonathan Le Roux
Target speech extraction aims to extract, based on a given conditioning cue, a target speech signal that is corrupted by interfering sources, such as noise or competing speakers. Building upon the achievements of the state-of-the-art (SOTA) time-frequency speaker separation model TF-GridNet, we propose AV-GridNet, a visual-grounded variant that incorporates the face recording of a target speaker as a conditioning factor during the extraction process. Recognizing the inherent dissimilarities between speech and noise signals as interfering sources, we also propose SAV-GridNet, a scenario-aware model that identifies the type of interfering scenario first and then applies a dedicated expert model trained specifically for that scenario. Our proposed model achieves SOTA results on the second COG-MHEAR Audio-Visual Speech Enhancement Challenge, outperforming other models by a significant margin, objectively and in a listening test. We also perform an extensive analysis of the results under the two scenarios.
PDF Accepted by ASRU 2023
点此查看论文截图
Breathing Life into Faces: Speech-driven 3D Facial Animation with Natural Head Pose and Detailed Shape
Authors:Wei Zhao, Yijun Wang, Tianyu He, Lianying Yin, Jianxin Lin, Xin Jin
The creation of lifelike speech-driven 3D facial animation requires a natural and precise synchronization between audio input and facial expressions. However, existing works still fail to render shapes with flexible head poses and natural facial details (e.g., wrinkles). This limitation is mainly due to two aspects: 1) Collecting training set with detailed 3D facial shapes is highly expensive. This scarcity of detailed shape annotations hinders the training of models with expressive facial animation. 2) Compared to mouth movement, the head pose is much less correlated to speech content. Consequently, concurrent modeling of both mouth movement and head pose yields the lack of facial movement controllability. To address these challenges, we introduce VividTalker, a new framework designed to facilitate speech-driven 3D facial animation characterized by flexible head pose and natural facial details. Specifically, we explicitly disentangle facial animation into head pose and mouth movement and encode them separately into discrete latent spaces. Then, these attributes are generated through an autoregressive process leveraging a window-based Transformer architecture. To augment the richness of 3D facial animation, we construct a new 3D dataset with detailed shapes and learn to synthesize facial details in line with speech content. Extensive quantitative and qualitative experiments demonstrate that VividTalker outperforms state-of-the-art methods, resulting in vivid and realistic speech-driven 3D facial animation.
PDF
点此查看论文截图
RIR-SF: Room Impulse Response Based Spatial Feature for Multi-channel Multi-talker ASR
Authors:Yiwen Shao, Shi-Xiong Zhang, Dong Yu
Multi-channel multi-talker automatic speech recognition (ASR) presents ongoing challenges within the speech community, particularly when confronted with significant reverberation effects. In this study, we introduce a novel approach involving the convolution of overlapping speech signals with the room impulse response (RIR) corresponding to the target speaker’s transmission to a microphone array. This innovative technique yields a novel spatial feature known as the RIR-SF. Through a comprehensive comparison with the previously established state-of-the-art 3D spatial feature, both theoretical analysis and experimental results substantiate the superiority of our proposed RIR-SF. We demonstrate that the RIR-SF outperforms existing methods, leading to a remarkable 21.3\% relative reduction in the Character Error Rate (CER) in multi-channel multi-talker ASR systems. Importantly, this novel feature exhibits robustness in the face of strong reverberation, surpassing the limitations of previous approaches.
PDF
点此查看论文截图
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning
Authors:Yongjin Yang, Joonkee Kim, Yujin Kim, Namgyu Ho, James Thorne, Se-young Yun
With the proliferation of social media, accurate detection of hate speech has become critical to ensure safety online. To combat nuanced forms of hate speech, it is important to identify and thoroughly explain hate speech to help users understand its harmful effects. Recent benchmarks have attempted to tackle this issue by training generative models on free-text annotations of implications in hateful text. However, we find significant reasoning gaps in the existing annotations schemes, which may hinder the supervision of detection models. In this paper, we introduce a hate speech detection framework, HARE, which harnesses the reasoning capabilities of large language models (LLMs) to fill these gaps in explanations of hate speech, thus enabling effective supervision of detection models. Experiments on SBIC and Implicit Hate benchmarks show that our method, using model-generated data, consistently outperforms baselines, using existing free-text human annotations. Analysis demonstrates that our method enhances the explanation quality of trained models and improves generalization to unseen datasets. Our code is available at https://github.com/joonkeekim/hare-hate-speech.git.
PDF Findings of EMNLP 2023; The first three authors contribute equally
点此查看论文截图
An analysis of large speech models-based representations for speech emotion recognition
Authors:Adrian Bogdan Stânea, Vlad Striletchi, Cosmin Striletchi, Adriana Stan
Large speech models-derived features have recently shown increased performance over signal-based features across multiple downstream tasks, even when the networks are not finetuned towards the target task. In this paper we show the results of an analysis of several signal- and neural models-derived features for speech emotion recognition. We use pretrained models and explore their inherent potential abstractions of emotions. Simple classification methods are used so as to not interfere or add knowledge to the task. We show that, even without finetuning, some of these large neural speech models’ representations can enclose information that enables performances close to, and even beyond state-of-the-art results across six standard speech emotion recognition datasets.
PDF Presented at SPED2023 - IEEE 12th Conference on Speech Technology and Human-Computer Dialogue, october 2023, Bucharest, Romania
点此查看论文截图
Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling
Authors:Sanchit Gandhi, Patrick von Platen, Alexander M. Rush
As the size of pre-trained speech recognition models increases, running these large models in low-latency or resource-constrained environments becomes challenging. In this work, we leverage pseudo-labelling to assemble a large-scale open-source dataset which we use to distill the Whisper model into a smaller variant, called Distil-Whisper. Using a simple word error rate (WER) heuristic, we select only the highest quality pseudo-labels for training. The distilled model is 5.8 times faster with 51% fewer parameters, while performing to within 1% WER on out-of-distribution test data in a zero-shot transfer setting. Distil-Whisper maintains the robustness of the Whisper model to difficult acoustic conditions, while being less prone to hallucination errors on long-form audio. Distil-Whisper is designed to be paired with Whisper for speculative decoding, yielding a 2 times speed-up while mathematically ensuring the same outputs as the original model. To facilitate further research in this domain, we make our training code, inference code and models publicly accessible.
PDF 30 pages, 2 figures, 25 tables
点此查看论文截图
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
Authors:Juan Zuluaga-Gomez, Zhaocheng Huang, Xing Niu, Rohit Paturi, Sundararajan Srinivasan, Prashant Mathur, Brian Thompson, Marcello Federico
Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers. In this paper, we tackle single-channel multi-speaker conversational ST with an end-to-end and multi-task training model, named Speaker-Turn Aware Conversational Speech Translation, that combines automatic speech recognition, speech translation and speaker turn detection using special tokens in a serialized labeling format. We run experiments on the Fisher-CALLHOME corpus, which we adapted by merging the two single-speaker channels into one multi-speaker channel, thus representing the more realistic and challenging scenario with multi-speaker turns and cross-talk. Experimental results across single- and multi-speaker conditions and against conventional ST systems, show that our model outperforms the reference systems on the multi-speaker condition, while attaining comparable performance on the single-speaker condition. We release scripts for data processing and model training.
PDF Accepted at EMNLP 2023. Code: https://github.com/amazon-science/stac-speech-translation
点此查看论文截图
Automatic Disfluency Detection from Untranscribed Speech
Authors:Amrit Romana, Kazuhito Koishida, Emily Mower Provost
Speech disfluencies, such as filled pauses or repetitions, are disruptions in the typical flow of speech. Stuttering is a speech disorder characterized by a high rate of disfluencies, but all individuals speak with some disfluencies and the rates of disfluencies may by increased by factors such as cognitive load. Clinically, automatic disfluency detection may help in treatment planning for individuals who stutter. Outside of the clinic, automatic disfluency detection may serve as a pre-processing step to improve natural language understanding in downstream applications. With this wide range of applications in mind, we investigate language, acoustic, and multimodal methods for frame-level automatic disfluency detection and categorization. Each of these methods relies on audio as an input. First, we evaluate several automatic speech recognition (ASR) systems in terms of their ability to transcribe disfluencies, measured using disfluency error rates. We then use these ASR transcripts as input to a language-based disfluency detection model. We find that disfluency detection performance is largely limited by the quality of transcripts and alignments. We find that an acoustic-based approach that does not require transcription as an intermediate step outperforms the ASR language approach. Finally, we present multimodal architectures which we find improve disfluency detection performance over the unimodal approaches. Ultimately, this work introduces novel approaches for automatic frame-level disfluency and categorization. In the long term, this will help researchers incorporate automatic disfluency detection into a range of applications.
PDF
点此查看论文截图