All-neural beamformer for continuous speech separation release_xutqsekhofb3ljeh5h6wxgukgu

by Zhuohuang Zhang, Takuya Yoshioka, Naoyuki Kanda, Zhuo Chen, Xiaofei Wang, Dongmei Wang, Sefik Emre Eskimez

Released as a article .

2021  

Abstract

Continuous speech separation (CSS) aims to separate overlapping voices from a continuous influx of conversational audio containing an unknown number of utterances spoken by an unknown number of speakers. A common application scenario is transcribing a meeting conversation recorded by a microphone array. Prior studies explored various deep learning models for time-frequency mask estimation, followed by a minimum variance distortionless response (MVDR) filter to improve the automatic speech recognition (ASR) accuracy. The performance of these methods is fundamentally upper-bounded by MVDR's spatial selectivity. Recently, the all deep learning MVDR (ADL-MVDR) model was proposed for neural beamforming and demonstrated superior performance in a target speech extraction task using pre-segmented input. In this paper, we further adapt ADL-MVDR to the CSS task with several enhancements to enable end-to-end neural beamforming. The proposed system achieves significant word error rate reduction over a baseline spectral masking system on the LibriCSS dataset. Moreover, the proposed neural beamformer is shown to be comparable to a state-of-the-art MVDR-based system in real meeting transcription tasks, including AMI, while showing potentials to further simplify the runtime implementation and reduce the system latency with frame-wise processing.
In text/plain format

Archived Files and Locations

application/pdf  820.9 kB
file_5ya3lq34xvbkni7hzqjskhojx4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-10-13
Version   v1
Language   en ?
arXiv  2110.06428v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bd0623eb-d958-476f-b835-a7fed5709612
API URL: JSON