@inproceedings{f9791f86e3ff42f49e61e1818ab0064b,
title = "Time Domain Audio Visual Speech Separation",
abstract = "Audio-visual multi-modal modeling has been demonstrated to be effective in many speech related tasks, such as speech recognition and speech enhancement. This paper introduces a new time-domain audio-visual architecture for target speaker extraction from monaural mixtures. The architecture generalizes the previous TasNet (time-domain speech separation network) to enable multi-modal learning and at meanwhile it extends the classical audio-visual speech separation from frequency-domain to time-domain. The main components of proposed architecture include an audio encoder, a video encoder that extracts lip embedding from video streams, a multi-modal separation network and an audio decoder. Experiments on simulated mixtures based on recently released LRS2 dataset show that our method can bring 3dB+ and 4dB+ Si-SNR improvements on two-and three-speaker cases respectively, compared to audio-only TasNet and frequency-domain audio-visual networks.",
keywords = "TasNet, audio-visual speech separation, multi-modal learning, speech enhancement",
author = "Jian Wu and Yong Xu and Zhang, {Shi Xiong} and Chen, {Lian Wu} and Meng Yu and Lei Xie and Dong Yu",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 ; Conference date: 15-12-2019 Through 18-12-2019",
year = "2019",
month = dec,
doi = "10.1109/ASRU46091.2019.9003983",
language = "英语",
series = "2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "667--673",
booktitle = "2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings",
}