Sa-Paraformer: Non-Autoregressive End-To-End Speaker-Attributed ASR

Yangze Li, Fan Yu, Yuhao Liang, Pengcheng Guo, Mohan Shi, Zhihao Du, Shiliang Zhang, Lei Xie

科研成果: 书/报告/会议事项章节会议稿件同行评审

4 引用 (Scopus)

摘要

Joint modeling of multi-speaker ASR and speaker diarization has recently shown promising results in speaker-attributed automatic speech recognition (SA-ASR). Although being able to obtain state-of-the-art (SOTA) performance, most of the studies are based on an autoregressive (AR) decoder which generates tokens one-by-one and results in a large real-time factor (RTF). To speed up inference, we introduce a recently proposed non-autoregressive model Paraformer as an acoustic model in the SA-ASR model. Paraformer uses a single-step decoder to enable parallel generation, obtaining comparable performance to the SOTA AR transformer models. Besides, we propose a speaker-filling strategy to reduce speaker identification errors and adopt an inter-CTC strategy to enhance the encoder's ability in acoustic modeling. Experiments on the AliMeeting corpus show that our model outperforms the cascaded SA-ASR model by a 6.1% relative speaker-dependent character error rate (SD-CER) reduction on the test set. Moreover, our model achieves a comparable SD-CER of 34.8% with only 1/10 RTF compared with the SOTA joint AR SA-ASR model.

源语言英语
主期刊名2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9798350306897
DOI
出版状态已出版 - 2023
活动2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 - Taipei, 中国台湾
期限: 16 12月 202320 12月 2023

出版系列

姓名2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

会议

会议2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
国家/地区中国台湾
Taipei
时期16/12/2320/12/23

指纹

探究 'Sa-Paraformer: Non-Autoregressive End-To-End Speaker-Attributed ASR' 的科研主题。它们共同构成独一无二的指纹。

引用此