English

Continuous Speech Separation with Conformer

Audio and Speech Processing 2020-10-23 v2 Computation and Language

Abstract

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and conformer in lieu of recurrent neural networks in the separation system, as we believe capturing global information with the self-attention based method is crucial for the speech separation. Evaluating on the LibriCSS dataset, the conformer separation model achieves state of the art results, with a relative 23.5% word error rate (WER) reduction from bi-directional LSTM (BLSTM) in the utterance-wise evaluation and a 15.4% WER reduction in the continuous evaluation.

Keywords

Cite

@article{arxiv.2008.05773,
  title  = {Continuous Speech Separation with Conformer},
  author = {Sanyuan Chen and Yu Wu and Zhuo Chen and Jian Wu and Jinyu Li and Takuya Yoshioka and Chengyi Wang and Shujie Liu and Ming Zhou},
  journal= {arXiv preprint arXiv:2008.05773},
  year   = {2020}
}
R2 v1 2026-06-23T17:49:47.947Z