2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)最新文献_第8页

HASA-Net: A Non-Intrusive Hearing-Aid Speech Assessment Network 非侵入式助听器语音评估网络

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-11-10 DOI: 10.1109/ASRU51503.2021.9687972

Hsin-Tien Chiang, Yi-Chiao Wu, Cheng Yu, T. Toda, Hsin-Min Wang, Yih-Chun Hu, Yu Tsao

{"title":"HASA-Net: A Non-Intrusive Hearing-Aid Speech Assessment Network","authors":"Hsin-Tien Chiang, Yi-Chiao Wu, Cheng Yu, T. Toda, Hsin-Min Wang, Yih-Chun Hu, Yu Tsao","doi":"10.1109/ASRU51503.2021.9687972","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9687972","url":null,"abstract":"Without the need of a clean reference, non-intrusive speech assessment methods have caught great attention for objective evaluations. Recently, deep neural network (DNN) models have been applied to build non-intrusive speech assessment approaches and confirmed to provide promising performance. However, most DNN-based approaches are designed for normal-hearing listeners without considering hearing-loss factors. In this study, we propose a DNN-based hearing aid speech assessment network (HASA-Net), formed by a bidirectional long short-term memory (BLSTM) model, to predict speech quality and intelligibility scores simultaneously according to input speech signals and specified hearing-loss patterns. To the best of our knowledge, HASA-Net is the first work to incorporate quality and intelligibility assessments utilizing a unified DNN-based non-intrusive model for hearing aids. Experimental results show that the predicted speech quality and intelligibility scores of HASA-Net are highly correlated to two well-known intrusive hearing-aid evaluation metrics, hearing aid speech quality index (HASQI) and hearing aid speech perception index (HASPI), respectively.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131875626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Context-Aware Transformer Transducer for Speech Recognition 用于语音识别的上下文感知变压器传感器

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-11-05 DOI: 10.1109/ASRU51503.2021.9687895

Feng-Ju Chang, Jing Liu, Martin H. Radfar, A. Mouchtaris, M. Omologo, A. Rastrow, S. Kunzmann

{"title":"Context-Aware Transformer Transducer for Speech Recognition","authors":"Feng-Ju Chang, Jing Liu, Martin H. Radfar, A. Mouchtaris, M. Omologo, A. Rastrow, S. Kunzmann","doi":"10.1109/ASRU51503.2021.9687895","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9687895","url":null,"abstract":"End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to latch onto personalized/contextual information at inference. In this work, we present a novel context-aware transformer transducer (CATT) network that improves the state-of-the-art transformer-based ASR system by taking advantage of such contextual signals. Specifically, we propose a multi-head attention-based context-biasing network, which is jointly trained with the rest of the ASR sub-networks. We explore different techniques to encode contextual data and to create the final attention context vectors. We also leverage both BLSTM and pretrained BERT based models to encode contextual data and guide the network training. Using an in-house far-field dataset, we show that CATT, using a BERT based context encoder, improves the word error rate of the baseline transformer transducer and outperforms an existing deep contextual model by 24.2% and 19.4% respectively.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128299872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 38

Cross-Lingual Transfer for Speech Processing Using Acoustic Language Similarity 基于声学语言相似性的语音处理跨语迁移

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-11-02 DOI: 10.1109/ASRU51503.2021.9688276

Peter Wu, Jiatong Shi, Yifan Zhong, Shinji Watanabe, A. Black

引用次数: 3

Cross-Attention Conformer for Context Modeling in Speech Enhancement for ASR ASR语音增强中上下文建模的交叉注意共形器

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-10-30 DOI: 10.1109/ASRU51503.2021.9688173

A. Narayanan, C. Chiu, Tom O'Malley, Quan Wang, Yanzhang He

引用次数: 13

Speaker Conditioning of Acoustic Models Using Affine Transformation for Multi-Speaker Speech Recognition 基于仿射变换的多说话人语音识别声学模型的说话人调节

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-10-30 DOI: 10.1109/ASRU51503.2021.9688231

Midia Yousefi, John H.L. Hanse

{"title":"Speaker Conditioning of Acoustic Models Using Affine Transformation for Multi-Speaker Speech Recognition","authors":"Midia Yousefi, John H.L. Hanse","doi":"10.1109/ASRU51503.2021.9688231","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9688231","url":null,"abstract":"This study addresses the problem of single-channel Automatic Speech Recognition of a target speaker within an overlap speech scenario. In the proposed method, the hidden representations in the acoustic model are modulated by speaker auxiliary information to recognize only the desired speaker. Affine transformation layers are inserted into the acoustic model network to integrate speaker information with the acoustic features. The speaker conditioning process allows the acoustic model to perform computation in the context of target-speaker auxiliary information. The proposed speaker conditioning method is a general approach and can be applied to any acoustic model architecture. Here, we employ speaker conditioning on a ResNet acoustic model. Experiments on the WSJ corpus show that the proposed speaker conditioning method is an effective solution to fuse speaker auxiliary information with acoustic features for multi-speaker speech recognition, achieving +9% and +20% relative WER reduction for clean and overlap speech scenarios, respectively, compared to the original ResNet acoustic model baseline.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132351982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Assessing Evaluation Metrics for Speech-to-Speech Translation 评估语音到语音翻译的评价指标

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-10-26 DOI: 10.1109/ASRU51503.2021.9688073

Elizabeth Salesky, Julian Mäder, Severin Klinger

引用次数: 9

Duality Temporal-Channel-Frequency Attention Enhanced Speaker Representation Learning 双重性时间-通道-频率注意增强说话人表征学习

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-10-13 DOI: 10.1109/ASRU51503.2021.9688243

Li Zhang, Qing Wang, Lei Xie

{"title":"Duality Temporal-Channel-Frequency Attention Enhanced Speaker Representation Learning","authors":"Li Zhang, Qing Wang, Lei Xie","doi":"10.1109/ASRU51503.2021.9688243","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9688243","url":null,"abstract":"The use of channel-wise attention in CNN based speaker representation networks has achieved remarkable performance in speaker verification (SV). But these approaches do simple averaging on time and frequency feature maps before channel-wise attention learning and ignore the essential mutual interaction among temporal, channel as well as frequency scales. To address this problem, we propose the Duality Temporal-Channel-Frequency (DTCF) attention to re-calibrate the channel-wise features with aggregation of global context on temporal and frequency dimensions. Specifically, the duality attention - time-channel (T-C) attention as well as frequency-channel (F-C) attention - aims to focus on salient regions along the T-C and F-C feature maps that may have more considerable impact on the global context, leading to more discriminative speaker representations. We evaluate the effectiveness of the proposed DTCF attention on the CN-Celeb and VoxCeleb datasets. On the CN-Celeb evaluation set, the EER/minDCF of ResNet34-DTCF are reduced by 0.63%/0.0718 compared with those of ResNet34-SE. On VoxCeleb1-O, VoxCeleb1-E and VoxCeleb1-H evaluation sets, the EER/minDCF of ResNet34-DTCF achieve 0.36%/0.0263, 0.39%/0.0382 and 0.74%/0.0753 reductions compared with those of ResNet34-SE.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122346782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

DEEPA: A Deep Neural Analyzer for Speech and Singing Vocoding DEEPA:用于语音和歌唱语音编码的深度神经分析仪

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-10-13 DOI: 10.1109/ASRU51503.2021.9687923

Sergey Nikonorov, Berrak Sisman, Mingyang Zhang, Haizhou Li

{"title":"DEEPA: A Deep Neural Analyzer for Speech and Singing Vocoding","authors":"Sergey Nikonorov, Berrak Sisman, Mingyang Zhang, Haizhou Li","doi":"10.1109/ASRU51503.2021.9687923","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9687923","url":null,"abstract":"Conventional vocoders are commonly used as analysis tools to provide interpretable features for downstream tasks such as speech synthesis and voice conversion. They are built under certain assumptions about the signals following signal processing principle, therefore, not easily generalizable to different audio, for example, from speech to singing. In this paper, we propose a deep neural analyzer, denoted as DeepA – a neural vocoder that extracts F0 and timbre/aperiodicity encoding from the input speech that emulate those defined in conventional vocoders. Therefore, the resulting parameters are more interpretable than other latent neural representations. At the same time, as the deep neural analyzer is learnable, it is expected to be more accurate for signal reconstruction and manipulation, and generalizable from speech to singing. The proposed neural analyzer is built based on a variational autoencoder (VAE) architecture. We show that DeepA improves F0 estimation over the conventional vocoder (WORLD). To our best knowledge, this is the first study dedicated to the development of a neural framework for extracting learnable vocoder-like parameters.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129646740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition 端到端语音识别中自监督预训练表征的探索

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-10-09 DOI: 10.1109/ASRU51503.2021.9688137

Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, A. Subramanian, Tianzi Wang, Shu-wen Yang, Yu Tsao, Hung-yi Lee, Shinji Watanabe

{"title":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","authors":"Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, A. Subramanian, Tianzi Wang, Shu-wen Yang, Yu Tsao, Hung-yi Lee, Shinji Watanabe","doi":"10.1109/ASRU51503.2021.9688137","DOIUrl":"https://doi.org/10.1109/ASRU51503.2021.9688137","url":null,"abstract":"Self-supervised pretraining on speech data has achieved a lot of progress. High-fidelity representation of the speech signal is learned from a lot of untranscribed data and shows promising performance. Recently, there are several works focusing on evaluating the quality of self-supervised pretrained representations on various tasks with-out domain restriction, e.g. SUPERB. However, such evaluations do not provide a comprehensive comparison among many ASR benchmark corpora. In this paper, we focus on the general applications of pretrained speech representations, on advanced end-to-end automatic speech recognition (E2E-ASR) models. We select sev-eral pretrained speech representations and present the experimental results on various open-source and publicly available corpora for E2E-ASR. Without any modification of the back-end model archi-tectures or training strategy, some of the experiments with pretrained representations, e.g., WSJ, WSJ0-2mix with HuBERT, reach or out-perform current state-of-the-art (SOTA) recognition performance. Moreover, we further explore more scenarios for whether the pre-training representations are effective, such as the cross-language or overlapped speech. The scripts, configuratons and the trained mod-els have been released in ESPnet to let the community reproduce our experiments and improve them.","PeriodicalId":348315,"journal":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123905415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 49

On the Invertibility of a Voice Privacy System Using Embedding Alignment 基于嵌入对齐的语音隐私系统可逆性研究

2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Pub Date : 2021-10-08 DOI: 10.1109/ASRU51503.2021.9688159

Pierre Champion, Thomas Thebaud, Gaël Le Lan, A. Larcher, D. Jouvet

引用次数: 2