Interspeech最新文献_第4页

Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection 呼吸和语音信号的声学表示学习用于COVID-19检测

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/interspeech.2022-10376

Debottam Dutta, Debarpan Bhattacharya, Sriram Ganapathy, A. H. Poorjam, Deepak Mittal, M. Singh

{"title":"Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection","authors":"Debottam Dutta, Debarpan Bhattacharya, Sriram Ganapathy, A. H. Poorjam, Deepak Mittal, M. Singh","doi":"10.21437/interspeech.2022-10376","DOIUrl":"https://doi.org/10.21437/interspeech.2022-10376","url":null,"abstract":"In this paper, we describe an approach for representation learning of audio signals for the task of COVID-19 detection. The raw audio samples are processed with a bank of 1-D convolutional filters that are parameterized as cosine modulated Gaussian functions. The choice of these kernels allows the interpretation of the filterbanks as smooth band-pass filters. The filtered outputs are pooled, log-compressed and used in a self-attention based relevance weighting mechanism. The relevance weighting emphasizes the key regions of the time-frequency decomposition that are important for the downstream task. The subsequent layers of the model consist of a recurrent architecture and the models are trained for a COVID-19 detection task. In our experiments on the Coswara data set, we show that the proposed model achieves significant performance improvements over the baseline system as well as other representation learning approaches. Further, the approach proposed is shown to be uniformly applicable for speech and breathing signals and for transfer learning from a larger data set. Copyright © 2022 ISCA.","PeriodicalId":73500,"journal":{"name":"Interspeech","volume":"1 1","pages":"2863-2867"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47618169","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

Japanese ASR-Robust Pre-trained Language Model with Pseudo-Error Sentences Generated by Grapheme-Phoneme Conversion 日语asr -鲁棒预训练的伪错误句模型

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/interspeech.2022-327

Yasuhito Ohsugi, Itsumi Saito, Kyosuke Nishida, Sen Yoshida

引用次数: 0

Bottom-up discovery of structure and variation in response tokens ('backchannels') across diverse languages 自下而上发现不同语言中响应令牌（“后台通道”）的结构和变化

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/interspeech.2022-11288

Andreas Liesenfeld, Mark Dingemanse

引用次数: 3

FlowCPCVC: A Contrastive Predictive Coding Supervised Flow Framework for Any-to-Any Voice Conversion FlowCPCVC：一种用于任意语音转换的对比预测编码监督流框架

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/interspeech.2022-577

Jiahong Huang, Wen Xu, Yule Li, Junshi Liu, Dongpeng Ma, Wei Xiang

{"title":"FlowCPCVC: A Contrastive Predictive Coding Supervised Flow Framework for Any-to-Any Voice Conversion","authors":"Jiahong Huang, Wen Xu, Yule Li, Junshi Liu, Dongpeng Ma, Wei Xiang","doi":"10.21437/interspeech.2022-577","DOIUrl":"https://doi.org/10.21437/interspeech.2022-577","url":null,"abstract":"Recently, the research of any-to-any voice conversion(VC) has been developed rapidly. However, they often suffer from unsat-isfactory quality and require two stages for training, in which a spectrum generation process is indispensable. In this paper, we propose the FlowCPCVC system, which results in higher speech naturalness and timbre similarity. FlowCPCVC is the first one-stage training system for any-to-any task in our knowledge by taking advantage of VAE and contrastive learning. We employ a speaker encoder to extract timbre information, and a contrastive predictive coding(CPC) based content extractor to guide the flow module to discard the timbre and keeping the linguistic information. Our method directly incorporates the vocoder into the training, thus avoiding the loss of spectral information as in two-stage training. With a fancy method in training any-to-any task, we can also get robust results when using it in any-to-many conversion. Experiments show that FlowCPCVC achieves obvious improvement when compared to VQMIVC which is current state-of-the-art any-to-any voice conversion system. Our demo is available online 1 .","PeriodicalId":73500,"journal":{"name":"Interspeech","volume":"1 1","pages":"2558-2562"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48445659","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: 3

Reducing Domain mismatch in Self-supervised speech pre-training 减少自监督语音预训练中的域不匹配

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/interspeech.2022-736

M. Baskar, A. Rosenberg, B. Ramabhadran, Yu Zhang, Nicolás Serrano

{"title":"Reducing Domain mismatch in Self-supervised speech pre-training","authors":"M. Baskar, A. Rosenberg, B. Ramabhadran, Yu Zhang, Nicolás Serrano","doi":"10.21437/interspeech.2022-736","DOIUrl":"https://doi.org/10.21437/interspeech.2022-736","url":null,"abstract":"Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems, they have one major limitation. They treat all unsupervised speech samples with equal weight, which hinders learning as not all samples have relevant information to learn meaningful representations. In this work, we address this limitation. We propose ask2mask (ATM), a novel approach to focus on speciﬁc samples during MSM pre-training. ATM employs an external ASR model or scorer to weight unsupervised input samples by performing a ﬁne-grained data selection. ATM performs masking over the highly conﬁdent input frames as chosen by the scorer. This allows the model to learn meaningful representations. We conduct ﬁne-tuning experiments on two well-benchmarked cor-pora: LibriSpeech (matching the pre-training data) and, AMI and CHiME-6 (not matching the pre-training data). The results substantiate the efﬁcacy of ATM on signiﬁcantly improving the recognition performance under mismatched conditions while still yielding modest improvements under matched conditions.","PeriodicalId":73500,"journal":{"name":"Interspeech","volume":"1 1","pages":"3028-3032"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48701115","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: 0

Perceptual Evaluation of Penetrating Voices through a Semantic Differential Method 语义差分法对穿透性语音的感知评价

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/interspeech.2022-100

T. Kitamura, Naoki Kunimoto, Hideki Kawahara, S. Amano

引用次数: 0

CALM: Constrastive Cross-modal Speaking Style Modeling for Expressive Text-to-Speech Synthesis 用于表达文本到语音合成的约束跨模态说话风格建模

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/interspeech.2022-11275

Yi Meng, Xiang Li, Zhiyong Wu, Tingtian Li, Zixun Sun, Xinyu Xiao, Chi Sun, Hui Zhan, H. Meng

引用次数: 4

Spatial-aware Speaker Diarization for Multi-channel Multi-party Meeting 基于空间感知的多渠道多方会议发言人日记

Interspeech Pub Date : 2022-09-18 DOI: 10.21437/Interspeech.2022-11412

Jie Wang, Yuji Liu, Binling Wang, Yiming Zhi, Song Li, Shipeng Xia, Jiayang Zhang, Feng Tong, Lin Li, Q. Hong