A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio-Reference-Cited by-同舟云学术

A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio

Published:2021-12-13 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
language:
Short-container-title:

Author:

Kanda Naoyuki¹,Xiao Xiong¹,Wu Jian¹,Zhou Tianyan¹,Gaur Yashesh¹,Wang Xiaofei¹,Meng Zhong¹,Chen Zhuo¹,Yoshioka Takuya¹

Affiliation:

1. Microsoft Corp.,USA

Publisher

IEEE

Link

Reference56 articles.

5. Serialized output training for end-to-end overlapped speech recognition;kanda;Proc INTERSPEECH,0

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Sa-Paraformer: Non-Autoregressive End-To-End Speaker-Attributed ASR;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16

2. The Royalflush System of Speech Recognition for M2met Challenge;ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2022-05-23

3. Multi-Turn RNN-T for Streaming Recognition of Multi-Party Speech;ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2022-05-23