Toward Speech Separation in The Pre-Cocktail Party Problem with TasTas
arXiv:2009.03692
Abstract
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.
arXiv commentarXiv admin note: substantial text overlap with arXiv:1902.04891
References in corpus (5)
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Deep attractor network for single-microphone speaker separation
- Speaker-independent Speech Separation with Deep Attractor Network
- Voice Separation with an Unknown Number of Multiple Speakers
- Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation