Wangyou Zhang, Jing Shi, Chenda Li, Shinji Watanabe, Y. Qian
{"title":"缩小真实和仿真条件下时域多通道语音增强的差距","authors":"Wangyou Zhang, Jing Shi, Chenda Li, Shinji Watanabe, Y. Qian","doi":"10.1109/WASPAA52581.2021.9632720","DOIUrl":null,"url":null,"abstract":"The deep learning based time-domain models, e.g. Conv-TasNet, have shown great potential in both single-channel and multi-channel speech enhancement. However, many experiments on the time-domain speech enhancement model are done in simulated conditions, and it is not well studied whether the good performance can generalize to real-world scenarios. In this paper, we aim to provide an insightful investigation of applying multi-channel Conv-TasNet based speech enhancement to both simulation and real data. Our preliminary experiments show a large performance gap between the two conditions in terms of the ASR performance. Several approaches are applied to close this gap, including the integration of multi-channel Conv-TasNet into the beamforming model with various strategies, and the joint training of speech enhancement and speech recognition models. Our experiments on the CHiME-4 corpus show that our proposed approaches can greatly reduce the speech recognition performance discrepancy between simulation and real data, while preserving the strong speech enhancement capability in the frontend.","PeriodicalId":429900,"journal":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions\",\"authors\":\"Wangyou Zhang, Jing Shi, Chenda Li, Shinji Watanabe, Y. Qian\",\"doi\":\"10.1109/WASPAA52581.2021.9632720\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The deep learning based time-domain models, e.g. Conv-TasNet, have shown great potential in both single-channel and multi-channel speech enhancement. However, many experiments on the time-domain speech enhancement model are done in simulated conditions, and it is not well studied whether the good performance can generalize to real-world scenarios. In this paper, we aim to provide an insightful investigation of applying multi-channel Conv-TasNet based speech enhancement to both simulation and real data. Our preliminary experiments show a large performance gap between the two conditions in terms of the ASR performance. Several approaches are applied to close this gap, including the integration of multi-channel Conv-TasNet into the beamforming model with various strategies, and the joint training of speech enhancement and speech recognition models. Our experiments on the CHiME-4 corpus show that our proposed approaches can greatly reduce the speech recognition performance discrepancy between simulation and real data, while preserving the strong speech enhancement capability in the frontend.\",\"PeriodicalId\":429900,\"journal\":{\"name\":\"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)\",\"volume\":\"53 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-10-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WASPAA52581.2021.9632720\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WASPAA52581.2021.9632720","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
The deep learning based time-domain models, e.g. Conv-TasNet, have shown great potential in both single-channel and multi-channel speech enhancement. However, many experiments on the time-domain speech enhancement model are done in simulated conditions, and it is not well studied whether the good performance can generalize to real-world scenarios. In this paper, we aim to provide an insightful investigation of applying multi-channel Conv-TasNet based speech enhancement to both simulation and real data. Our preliminary experiments show a large performance gap between the two conditions in terms of the ASR performance. Several approaches are applied to close this gap, including the integration of multi-channel Conv-TasNet into the beamforming model with various strategies, and the joint training of speech enhancement and speech recognition models. Our experiments on the CHiME-4 corpus show that our proposed approaches can greatly reduce the speech recognition performance discrepancy between simulation and real data, while preserving the strong speech enhancement capability in the frontend.