CASA-ASR: Context-Aware Speaker-Attributed ASR
Abstract
Recently, speaker-attributed automatic speech recognition (SA-ASR) has attracted a wide attention, which aims at answering the question ``who spoke what''. Different from modular systems, end-to-end (E2E) SA-ASR minimizes the speaker-dependent recognition errors directly and shows a promising applicability. In this paper, we propose a context-aware SA-ASR (CASA-ASR) model by enhancing the contextual modeling ability of E2E SA-ASR. Specifically, in CASA-ASR, a contextual text encoder is involved to aggregate the semantic information of the whole utterance, and a context-dependent scorer is employed to model the speaker discriminability by contrasting with speakers in the context. In addition, a two-pass decoding strategy is further proposed to fully leverage the contextual modeling ability resulting in a better recognition performance. Experimental results on AliMeeting corpus show that the proposed CASA-ASR model outperforms the original E2E SA-ASR system with a relative improvement of 11.76% in terms of speaker-dependent character error rate.
Keywords
Cite
@article{arxiv.2305.12459,
title = {CASA-ASR: Context-Aware Speaker-Attributed ASR},
author = {Mohan Shi and Zhihao Du and Qian Chen and Fan Yu and Yangze Li and Shiliang Zhang and Jie Zhang and Li-Rong Dai},
journal= {arXiv preprint arXiv:2305.12459},
year = {2023}
}
Comments
Accepted by Interspeech2023