Multi-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment

TL;DR

This paper presents Solo-SF, a novel method that improves multi-channel, multi-speaker ASR by using a target speaker's isolated segment, achieving lower error rates without relying on microphone array configurations.

Contribution

Introducing Solo-SF, a new approach that leverages solo speech segments to enhance target speaker recognition in multi-channel ASR, bypassing traditional spatial information requirements.

Findings

Solo-SF outperforms existing methods in CER reduction.

Effective solo segment selection strategies are crucial for Solo-SF.

Demonstrated robustness across datasets and noise conditions.

Abstract

In the field of multi-channel, multi-speaker Automatic Speech Recognition (ASR), the task of discerning and accurately transcribing a target speaker's speech within background noise remains a formidable challenge. Traditional approaches often rely on microphone array configurations and the information of the target speaker's location or voiceprint. This study introduces the Solo Spatial Feature (Solo-SF), an innovative method that utilizes a target speaker's isolated speech segment to enhance ASR performance, thereby circumventing the need for conventional inputs like microphone array layouts. We explore effective strategies for selecting optimal solo segments, a crucial aspect for Solo-SF's success. Through evaluations conducted on the AliMeeting dataset and AISHELL-1 simulations, Solo-SF demonstrates superior performance over existing techniques, significantly lowering Character Error Rates (CER) in various test conditions. Our findings highlight Solo-SF's potential as an effective solution for addressing the complexities of multi-channel, multi-speaker ASR tasks.