Joint Unsupervised and Supervised Training for Multilingual ASR-Reference-Cited by-同舟云学术

Joint Unsupervised and Supervised Training for Multilingual ASR

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:

Bai Junwen¹,Li Bo¹,Zhang Yu¹,Bapna Ankur¹,Siddhartha Nikhil¹,Chai Sim Khe¹,Sainath Tara N.¹

Affiliation:

1. Google,USA

Publisher

IEEE

Link

Reference28 articles.

2. Continual-wav2vec2: an application of continual learning for self-supervised automatic speech recognition;kessler,2021

5. Cross-lingual language model pretraining;conneau;Advances in neural information processing systems,2019

Cited by 27 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. 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

2. Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Prompting Large Language Models with Speech Recognition Abilities;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14