English

Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis

Audio and Speech Processing 2020-11-05 v1 Sound

Abstract

Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation. With technical advances in systems dealing with speech separation, speaker diarization, and automatic speech recognition (ASR) in the last decade, it has become possible to build pipelines that achieve reasonable error rates on this task. In this paper, we propose an end-to-end modular system for the LibriCSS meeting data, which combines independently trained separation, diarization, and recognition components, in that order. We study the effect of different state-of-the-art methods at each stage of the pipeline, and report results using task-specific metrics like SDR and DER, as well as downstream WER. Experiments indicate that the problem of overlapping speech for diarization and ASR can be effectively mitigated with the presence of a well-trained separation module. Our best system achieves a speaker-attributed WER of 12.7%, which is close to that of a non-overlapping ASR.

Keywords

Cite

@article{arxiv.2011.02014,
  title  = {Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis},
  author = {Desh Raj and Pavel Denisov and Zhuo Chen and Hakan Erdogan and Zili Huang and Maokui He and Shinji Watanabe and Jun Du and Takuya Yoshioka and Yi Luo and Naoyuki Kanda and Jinyu Li and Scott Wisdom and John R. Hershey},
  journal= {arXiv preprint arXiv:2011.02014},
  year   = {2020}
}

Comments

Accepted to IEEE SLT 2021

R2 v1 2026-06-23T19:53:59.761Z