论文标题
taveas的前尾派对问题中的语音分离
Toward Speech Separation in The Pre-Cocktail Party Problem with TasTas
论文作者
论文摘要
在本说明中，我们建议使用tastas \ cite {shi2020-speech}进行端到端的端到端方法中的单声道分离方法。我们对公共WSJ0-5MIX数据语料库进行的实验可导致10.41DB SDR改进。如果在培训中采用了在线语音数据混音增强\ Cite {Zeghidour2020wavesplit}，则可以实现11.14DB SDR的改进。 We have open-sourced our re-implementation of the DPRNN-TasNet in https://github.com/ShiZiqiang/dual-path-RNNs-DPRNNs-based-speech-separation, and our TasTas is realized based on this implementation of DPRNN-TasNet, it is believed that the results in this paper can be reproduced with ease.
In this note, we propose to use TasTas \cite{shi2020speech} for the end-to-end approach to monaural speech separation in the pre-cocktail party problem. Our experiments on the public WSJ0-5mix data corpus results in 10.41dB SDR improvement. If online voice data remixing augmentation \cite{zeghidour2020wavesplit} is adopted in training, an 11.14dB SDR improvement can be achieved. We have open-sourced our re-implementation of the DPRNN-TasNet in https://github.com/ShiZiqiang/dual-path-RNNs-DPRNNs-based-speech-separation, and our TasTas is realized based on this implementation of DPRNN-TasNet, it is believed that the results in this paper can be reproduced with ease.
