Improving CTC-Based Speech Recognition Via Knowledge Transferring from Pre-Trained Language Models-Reference-Cited by-同舟云学术

Improving CTC-Based Speech Recognition Via Knowledge Transferring from Pre-Trained Language Models

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Deng Keqi¹,Cao Songjun²,Zhang Yike²,Ma Long²,Cheng Gaofeng¹,Xu Ji¹,Zhang Pengyuan¹

Affiliation:

1. Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China

2. Tencent Cloud Xiaowei,Beijing,China

Funder

Research and Development

Publisher

IEEE

Link

Reference32 articles.

5. Imputer: Sequence modelling via imputation and dynamic programming;chan;Proc ICML,2020

Cited by 17 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. Analyzing the Regularization Technique in Automatic Speech Recognition System Using Sepedi-English Code-Switched Data;2024 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD);2024-08-01

4. Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14