2023-03-04 更新
Multi-Channel Target Speaker Extraction with Refinement: The WavLab Submission to the Second Clarity Enhancement Challenge
Authors:Samuele Cornell, Zhong-Qiu Wang, Yoshiki Masuyama, Shinji Watanabe, Manuel Pariente, Nobutaka Ono
This paper describes our submission to the Second Clarity Enhancement Challenge (CEC2), which consists of target speech enhancement for hearing-aid (HA) devices in noisy-reverberant environments with multiple interferers such as music and competing speakers. Our approach builds upon the powerful iterative neural/beamforming enhancement (iNeuBe) framework introduced in our recent work, and this paper extends it for target speaker extraction. We therefore name the proposed approach as iNeuBe-X, where the X stands for extraction. To address the challenges encountered in the CEC2 setting, we introduce four major novelties: (1) we extend the state-of-the-art TF-GridNet model, originally designed for monaural speaker separation, for multi-channel, causal speech enhancement, and large improvements are observed by replacing the TCNDenseNet used in iNeuBe with this new architecture; (2) we leverage a recent dual window size approach with future-frame prediction to ensure that iNueBe-X satisfies the 5 ms constraint on algorithmic latency required by CEC2; (3) we introduce a novel speaker-conditioning branch for TF-GridNet to achieve target speaker extraction; (4) we propose a fine-tuning step, where we compute an additional loss with respect to the target speaker signal compensated with the listener audiogram. Without using external data, on the official development set our best model reaches a hearing-aid speech perception index (HASPI) score of 0.942 and a scale-invariant signal-to-distortion ratio improvement (SI-SDRi) of 18.8 dB. These results are promising given the fact that the CEC2 data is extremely challenging (e.g., on the development set the mixture SI-SDR is -12.3 dB). A demo of our submitted system is available at WAVLab CEC2 demo.
PDF
点此查看论文截图
Personalized speech enhancement combining band-split RNN and speaker attentive module
Authors:Xiaohuai Le, Zhongshu Hou, Li Chen, Chao He, Yiqing Guo, Cheng Chen, Xianjun Xia, Jing Lu
Target speaker information can be utilized in speech enhancement (SE) models to more effectively extract the desired speech. Previous works introduce the speaker embedding into speech enhancement models by means of concatenation or affine transformation. In this paper, we propose a speaker attentive module to calculate the attention scores between the speaker embedding and the intermediate features, which are used to rescale the features. By merging this module in the state-of-the-art SE model, we construct the personalized SE model for ICASSP Signal Processing Grand Challenge: DNS Challenge 5 (2023). Our system achieves a final score of 0.529 on the blind test set of track1 and 0.549 on track2.
PDF
点此查看论文截图
Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey
Authors:Xiao Wang, Guangyao Chen, Guangwu Qian, Pengcheng Gao, Xiao-Yong Wei, Yaowei Wang, Yonghong Tian, Wen Gao
With the urgent demand for generalized deep models, many pre-trained big models are proposed, such as BERT, ViT, GPT, etc. Inspired by the success of these models in single domains (like computer vision and natural language processing), the multi-modal pre-trained big models have also drawn more and more attention in recent years. In this work, we give a comprehensive survey of these models and hope this paper could provide new insights and helps fresh researchers to track the most cutting-edge works. Specifically, we firstly introduce the background of multi-modal pre-training by reviewing the conventional deep learning, pre-training works in natural language process, computer vision, and speech. Then, we introduce the task definition, key challenges, and advantages of multi-modal pre-training models (MM-PTMs), and discuss the MM-PTMs with a focus on data, objectives, network architectures, and knowledge enhanced pre-training. After that, we introduce the downstream tasks used for the validation of large-scale MM-PTMs, including generative, classification, and regression tasks. We also give visualization and analysis of the model parameters and results on representative downstream tasks. Finally, we point out possible research directions for this topic that may benefit future works. In addition, we maintain a continuously updated paper list for large-scale pre-trained multi-modal big models: https://github.com/wangxiao5791509/MultiModal_BigModels_Survey
PDF Accepted by Machine Intelligence Research
点此查看论文截图
Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation
Authors:Yuchen Hu, Chen Chen, Heqing Zou, Xionghu Zhong, Eng Siong Chng
Recent studies in neural network-based monaural speech separation (SS) have achieved a remarkable success thanks to increasing ability of long sequence modeling. However, they would degrade significantly when put under realistic noisy conditions, as the background noise could be mistaken for speaker’s speech and thus interfere with the separated sources. To alleviate this problem, we propose a novel network to unify speech enhancement and separation with gradient modulation to improve noise-robustness. Specifically, we first build a unified network by combining speech enhancement (SE) and separation modules, with multi-task learning for optimization, where SE is supervised by parallel clean mixture to reduce noise for downstream speech separation. Furthermore, in order to avoid suppressing valid speaker information when reducing noise, we propose a gradient modulation (GM) strategy to harmonize the SE and SS tasks from optimization view. Experimental results show that our approach achieves the state-of-the-art on large-scale Libri2Mix- and Libri3Mix-noisy datasets, with SI-SNRi results of 16.0 dB and 15.8 dB respectively. Our code is available at GitHub.
PDF 5 pages, 5 figures, Accepted by ICASSP 2023
点此查看论文截图
Frequency bin-wise single channel speech presence probability estimation using multiple DNNs
Authors:Shuai Tao, Himavanth Reddy, Jesper Rindom Jensen, Mads Græsbøll Christensen
In this work, we propose a frequency bin-wise method to estimate the single-channel speech presence probability (SPP) with multiple deep neural networks (DNNs) in the short-time Fourier transform domain. Since all frequency bins are typically considered simultaneously as input features for conventional DNN-based SPP estimators, high model complexity is inevitable. To reduce the model complexity and the requirements on the training data, we take a single frequency bin and some of its neighboring frequency bins into account to train separate gate recurrent units. In addition, the noisy speech and the a posteriori probability SPP representation are used to train our model. The experiments were performed on the Deep Noise Suppression challenge dataset. The experimental results show that the speech detection accuracy can be improved when we employ the frequency bin-wise model. Finally, we also demonstrate that our proposed method outperforms most of the state-of-the-art SPP estimation methods in terms of speech detection accuracy and model complexity.
PDF Accepted for ICASSP 2023
点此查看论文截图
DFSNet: A Steerable Neural Beamformer Invariant to Microphone Array Configuration for Real-Time, Low-Latency Speech Enhancement
Authors:Anton Kovalyov, Kashyap Patel, Issa Panahi
Invariance to microphone array configuration is a rare attribute in neural beamformers. Filter-and-sum (FS) methods in this class define the target signal with respect to a reference channel. However, this not only complicates formulation in reverberant conditions but also the network, which must have a mechanism to infer what the reference channel is. To address these issues, this study presents Delay Filter-and-Sum Network (DFSNet), a steerable neural beamformer invariant to microphone number and array geometry for causal speech enhancement. In DFSNet, acquired signals are first steered toward the speech source direction prior to the FS operation, which simplifies the task into the estimation of delay-and-summed reverberant clean speech. The proposed model is designed to incur low latency, distortion, and memory and computational burden, giving rise to high potential in hearing aid applications. Simulation results reveal comparable performance to noncausal state-of-the-art.
PDF 5 pages, 1 figure, 2 tables
点此查看论文截图
Diacritic Recognition Performance in Arabic ASR
Authors:Hanan Aldarmaki, Ahmad Ghannam
We present an analysis of diacritic recognition performance in Arabic Automatic Speech Recognition (ASR) systems. As most existing Arabic speech corpora do not contain all diacritical marks, which represent short vowels and other phonetic information in Arabic script, current state-of-the-art ASR models do not produce full diacritization in their output. Automatic text-based diacritization has previously been employed both as a pre-processing step to train diacritized ASR, or as a post-processing step to diacritize the resulting ASR hypotheses. It is generally believed that input diacritization degrades ASR performance, but no systematic evaluation of ASR diacritization performance, independent of ASR performance, has been conducted to date. In this paper, we attempt to experimentally clarify whether input diacritiztation indeed degrades ASR quality, and to compare the diacritic recognition performance against text-based diacritization as a post-processing step. We start with pre-trained Arabic ASR models and fine-tune them on transcribed speech data with different diacritization conditions: manual, automatic, and no diacritization. We isolate diacritic recognition performance from the overall ASR performance using coverage and precision metrics. We find that ASR diacritization significantly outperforms text-based diacritization in post-processing, particularly when the ASR model is fine-tuned with manually diacritized transcripts.
PDF
点此查看论文截图
Multimodal Speech Recognition for Language-Guided Embodied Agents
Authors:Allen Chang, Xiaoyuan Zhu, Aarav Monga, Seoho Ahn, Tejas Srinivasan, Jesse Thomason
Benchmarks for language-guided embodied agents typically assume text-based instructions, but deployed agents will encounter spoken instructions. While Automatic Speech Recognition (ASR) models can bridge the input gap, erroneous ASR transcripts can hurt the agents’ ability to complete tasks. In this work, we propose training a multimodal ASR model to reduce errors in transcribing spoken instructions by considering the accompanying visual context. We train our model on a dataset of spoken instructions, synthesized from the ALFRED task completion dataset, where we simulate acoustic noise by systematically masking spoken words. We find that utilizing visual observations facilitates masked word recovery, with multimodal ASR models recovering up to 30% more masked words than unimodal baselines. We also find that a text-trained embodied agent successfully completes tasks more often by following transcribed instructions from multimodal ASR models.
PDF 5 pages, 5 figures
点此查看论文截图
The 2022 NIST Language Recognition Evaluation
Authors:Yooyoung Lee, Craig Greenberg, Eliot Godard, Asad A. Butt, Elliot Singer, Trang Nguyen, Lisa Mason, Douglas Reynolds
In 2022, the U.S. National Institute of Standards and Technology (NIST) conducted the latest Language Recognition Evaluation (LRE) in an ongoing series administered by NIST since 1996 to foster research in language recognition and to measure state-of-the-art technology. Similar to previous LREs, LRE22 focused on conversational telephone speech (CTS) and broadcast narrowband speech (BNBS) data. LRE22 also introduced new evaluation features, such as an emphasis on African languages, including low resource languages, and a test set consisting of segments containing between 3s and 35s of speech randomly sampled and extracted from longer recordings. A total of 21 research organizations, forming 16 teams, participated in this 3-month long evaluation and made a total of 65 valid system submissions to be evaluated. This paper presents an overview of LRE22 and an analysis of system performance over different evaluation conditions. The evaluation results suggest that Oromo and Tigrinya are easier to detect while Xhosa and Zulu are more challenging. A greater confusability is seen for some language pairs. When speech duration increased, system performance significantly increased up to a certain duration, and then a diminishing return on system performance is observed afterward.
PDF 5 pages, 10 figures
点此查看论文截图
SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing
Authors:Weidong Chen, Xiaofen Xing, Xiangmin Xu, Jianxin Pang, Lan Du
Paralinguistic speech processing is important in addressing many issues, such as sentiment and neurocognitive disorder analyses. Recently, Transformer has achieved remarkable success in the natural language processing field and has demonstrated its adaptation to speech. However, previous works on Transformer in the speech field have not incorporated the properties of speech, leaving the full potential of Transformer unexplored. In this paper, we consider the characteristics of speech and propose a general structure-based framework, called SpeechFormer++, for paralinguistic speech processing. More concretely, following the component relationship in the speech signal, we design a unit encoder to model the intra- and inter-unit information (i.e., frames, phones, and words) efficiently. According to the hierarchical relationship, we utilize merging blocks to generate features at different granularities, which is consistent with the structural pattern in the speech signal. Moreover, a word encoder is introduced to integrate word-grained features into each unit encoder, which effectively balances fine-grained and coarse-grained information. SpeechFormer++ is evaluated on the speech emotion recognition (IEMOCAP & MELD), depression classification (DAIC-WOZ) and Alzheimer’s disease detection (Pitt) tasks. The results show that SpeechFormer++ outperforms the standard Transformer while greatly reducing the computational cost. Furthermore, it delivers superior results compared to the state-of-the-art approaches.
PDF 14 pages, 7 figures, 14 tables, TASLP 2023 paper
点此查看论文截图
Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement
Authors:Bunlong Lay, Simon Welker, Julius Richter, Timo Gerkmann
Recently, score-based generative models have been successfully employed for the task of speech enhancement. A stochastic differential equation is used to model the iterative forward process, where at each step environmental noise and white Gaussian noise are added to the clean speech signal. While in limit the mean of the forward process ends at the noisy mixture, in practice it stops earlier and thus only at an approximation of the noisy mixture. This results in a discrepancy between the terminating distribution of the forward process and the prior used for solving the reverse process at inference. In this paper, we address this discrepancy. To this end, we propose a forward process based on a Brownian bridge and show that such a process leads to a reduction of the mismatch compared to previous diffusion processes. More importantly, we show that our approach improves in objective metrics over the baseline process with only half of the iteration steps and having one hyperparameter less to tune.
PDF 5 pages, 3 figures
点此查看论文截图
N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space
Authors:Rao Ma, Mark J F Gales, Kate Knill, Mengjie Qian
Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions. Most prior works use the 1-best ASR hypothesis as input and therefore can only perform correction by leveraging the context within one sentence. In this work, we propose a novel N-best T5 model for this task, which is fine-tuned from a T5 model and utilizes ASR N-best lists as model input. By transferring knowledge from the pre-trained language model and obtaining richer information from the ASR decoding space, the proposed approach outperforms a strong Conformer-Transducer baseline. Another issue with standard error correction is that the generation process is not well-guided. To address this a constrained decoding process, either based on the N-best list or an ASR lattice, is used which allows additional information to be propagated.
PDF
点此查看论文截图
MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation
Authors:Mohamed Anwar, Bowen Shi, Vedanuj Goswami, Wei-Ning Hsu, Juan Pino, Changhan Wang
We introduce MuAViC, a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation providing 1200 hours of audio-visual speech in 9 languages. It is fully transcribed and covers 6 English-to-X translation as well as 6 X-to-English translation directions. To the best of our knowledge, this is the first open benchmark for audio-visual speech-to-text translation and the largest open benchmark for multilingual audio-visual speech recognition. Our baseline results show that MuAViC is effective for building noise-robust speech recognition and translation models. We make the corpus available at https://github.com/facebookresearch/muavic.
PDF
点此查看论文截图
Ego-noise reduction of a mobile robot using noise spatial covariance matrix learning and minimum variance distortionless response
Authors:Philippe-Olivier Lagacé, François Ferland, François Grondin
The performance of speech and events recognition systems significantly improved recently thanks to deep learning methods. However, some of these tasks remain challenging when algorithms are deployed on robots due to the unseen mechanical noise and electrical interference generated by their actuators while training the neural networks. Ego-noise reduction as a preprocessing step therefore can help solve this issue when using pre-trained speech and event recognition algorithms on robots. In this paper, we propose a new method to reduce ego-noise using only a microphone array and less than two minute of noise recordings. Using Principal Component Analysis (PCA), the best covariance matrix candidate is selected from a dictionary created online during calibration and used with the Minimum Variance Distortionless Response (MVDR) beamformer. Results show that the proposed method runs in real-time, improves the signal-to-distortion ratio (SDR) by up to 10 dB, decreases the word error rate (WER) by 55\% in some cases and increases the Average Precision (AP) of event detection by up to 0.2.
PDF Submitted to IROS 2023
点此查看论文截图
Leveraging Large Text Corpora for End-to-End Speech Summarization
Authors:Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Tomohiro Tanaka, Atsunori Ogawa, Marc Delcroix, Ryo Masumura
End-to-end speech summarization (E2E SSum) is a technique to directly generate summary sentences from speech. Compared with the cascade approach, which combines automatic speech recognition (ASR) and text summarization models, the E2E approach is more promising because it mitigates ASR errors, incorporates nonverbal information, and simplifies the overall system. However, since collecting a large amount of paired data (i.e., speech and summary) is difficult, the training data is usually insufficient to train a robust E2E SSum system. In this paper, we present two novel methods that leverage a large amount of external text summarization data for E2E SSum training. The first technique is to utilize a text-to-speech (TTS) system to generate synthesized speech, which is used for E2E SSum training with the text summary. The second is a TTS-free method that directly inputs phoneme sequence instead of synthesized speech to the E2E SSum model. Experiments show that our proposed TTS- and phoneme-based methods improve several metrics on the How2 dataset. In particular, our best system outperforms a previous state-of-the-art one by a large margin (i.e., METEOR score improvements of more than 6 points). To the best of our knowledge, this is the first work to use external language resources for E2E SSum. Moreover, we report a detailed analysis of the How2 dataset to confirm the validity of our proposed E2E SSum system.
PDF Accepted to ICASSP 2023
点此查看论文截图
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Authors:Yu Zhang, Wei Han, James Qin, Yongqiang Wang, Ankur Bapna, Zhehuai Chen, Nanxin Chen, Bo Li, Vera Axelrod, Gary Wang, Zhong Meng, Ke Hu, Andrew Rosenberg, Rohit Prabhavalkar, Daniel S. Park, Parisa Haghani, Jason Riesa, Ginger Perng, Hagen Soltau, Trevor Strohman, Bhuvana Ramabhadran, Tara Sainath, Pedro Moreno, Chung-Cheng Chiu, Johan Schalkwyk, Françoise Beaufays, Yonghui Wu
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages. This is achieved by pre-training the encoder of the model on a large unlabeled multilingual dataset of 12 million (M) hours spanning over 300 languages, and fine-tuning on a smaller labeled dataset. We use multilingual pre-training with random-projection quantization and speech-text modality matching to achieve state-of-the-art performance on downstream multilingual ASR and speech-to-text translation tasks. We also demonstrate that despite using a labeled training set 1/7-th the size of that used for the Whisper model, our model exhibits comparable or better performance on both in-domain and out-of-domain speech recognition tasks across many languages.
PDF 20 pages, 7 figures, 8 tables
点此查看论文截图
LiteG2P: A fast, light and high accuracy model for grapheme-to-phoneme conversion
Authors:Chunfeng Wang, Peisong Huang, Yuxiang Zou, Haoyu Zhang, Shichao Liu, Xiang Yin, Zejun Ma
As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations. Existing methods are either slow or poor in performance, and are limited in application scenarios, particularly in the process of on-device inference. In this paper, we integrate the advantages of both expert knowledge and connectionist temporal classification (CTC) based neural network and propose a novel method named LiteG2P which is fast, light and theoretically parallel. With the carefully leading design, LiteG2P can be applied both on cloud and on device. Experimental results on the CMU dataset show that the performance of the proposed method is superior to the state-of-the-art CTC based method with 10 times fewer parameters, and even comparable to the state-of-the-art Transformer-based sequence-to-sequence model with less parameters and 33 times less computation.
PDF Accepted by ICASSP2023
点此查看论文截图
Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech Recognition
Authors:Zhijie Shen, Wu Guo, Bin Gu
In this paper, we propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition (ASR). For acoustic modeling, the wav2vec 2.0 pre-trained model is fine-tuned by inserting language-specific and language-universal adapters. An online knowledge distillation is then used to enable the language-universal adapters to learn both language-specific and universal features. The linguistic information confusion is also reduced by leveraging language identifiers (LIDs). With LIDs we perform a position-wise modification on the multi-head attention outputs. In the inference procedure, the language-specific adapters are removed while the language-universal adapters are kept activated. The proposed method improves the recognition accuracy and addresses the linear increase of the number of adapters’ parameters with the number of languages in common multilingual ASR systems. Experiments on the BABEL dataset confirm the effectiveness of the proposed framework. Compared to the conventional multilingual model, a 3.3% absolute error rate reduction is achieved. The code is available at: https://github.com/shen9712/UniversalAdapterLearning.
PDF