@inproceedings{zhang2022all-neural,
author = {Zhang, Zhuohuang and Yoshioka, Takuya and Kanda, Naoyuki and Chen, Zhuo and Wang, Xiaofei and Wang, Dongmei and Eskimez, Sefik Emre},
title = {All-Neural Beamformer for Continuous Speech Separation},
organization = {IEEE},
booktitle = {ICASSP 2022},
year = {2022},
month = {May},
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.},
url = {http://approjects.co.za/?big=en-us/research/publication/all-neural-beamformer-for-continuous-speech-separation/},
}