Accelerating RNN-T Training and Inference Using CTC Guidance-Reference-Cited by-同舟云学术

Accelerating RNN-T Training and Inference Using CTC Guidance

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Wang Yongqiang¹,Chen Zhehuai¹,Zheng Chengjian¹,Zhang Yu¹,Han Wei¹,Haghani Parisa¹

Affiliation:

1. Google

Publisher

IEEE

Link

Reference30 articles.

1. Monotonic chunkwise attention;chiu,2017

4. Sequence transduction with recurrent neural networks;graves,2012

Cited by 7 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. Adapting Large Language Model with Speech for Fully Formatted End-to-End Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. Retrieval Augmented End-to-End Spoken Dialog Models;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. CIF-T: A Novel CIF-Based Transducer Architecture for Automatic Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. CTC Blank Triggered Dynamic Layer-Skipping for Efficient Ctc-Based Speech Recognition;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16