Multi-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks. In this study, we propose a pioneering approach to empower Whisper, which is a speech foundation model, to tackle joint multi-talker and target-talker speech recognition tasks. Specifically, (i) we freeze Whisper and plug a Sidecar separator into its encoder to separate mixed embedding for multiple talkers; (ii) a Target Talker Identifier is introduced to identify the embedding flow of the target talker on the fly, requiring only three-second enrollment speech as a cue; (iii) soft prompt tuning for decoder is explored for better task adaptation. Our method outperforms previous methods on two- and three-talker LibriMix and LibriSpeechMix datasets for both tasks, and delivers acceptable zero-shot performance on multi-talker ASR on AishellMix Mandarin dataset.
@article{arxiv.2407.09817,
title = {Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System},
author = {Lingwei Meng and Jiawen Kang and Yuejiao Wang and Zengrui Jin and Xixin Wu and Xunying Liu and Helen Meng},
journal= {arXiv preprint arXiv:2407.09817},
year = {2024}
}