@inproceedings{wu2021investigation,
author = {Wu, Jian and Chen, Zhuo and Chen, Sanyuan and Wu, Yu and Yoshioka, Takuya and Kanda, Naoyuki and Liu, Shujie and Li, Jinyu},
title = {Investigation of Practical Aspects of Single Channel Speech Separation for ASR},
booktitle = {Interspeech 2021},
year = {2021},
month = {August},
abstract = {Speech separation has been successfully applied as a front-end processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic speech recognition (ASR).
However, a speech separation model often introduces target speech distortion, resulting in a sub-optimum word error rate (WER).
In this paper, we describe our efforts to improve the performance of a single channel speech separation system. Specifically, we investigate a two-stage training scheme that firstly applies a feature level optimization criterion for pre-training, followed by an ASR-oriented optimization criterion using an end-to-end (E2E) speech recognition model.
Meanwhile, to keep the model light-weight, we introduce a modified teacher-student learning technique for model compression. By combining those approaches, we achieve an absolute average WER improvement of 2.70% and 0.77% using models with less than 10M parameters compared with the previous state-of-the-art results on the LibriCSS dataset for utterance-wise evaluation and continuous evaluation, respectively.},
url = {http://approjects.co.za/?big=en-us/research/publication/investigation-of-practical-aspects-of-single-channel-speech-separation-for-asr/},
}