BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder-Reference-Cited by-同舟云学术

BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder

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:

Higuchi Yosuke¹,Ogawa Tetsuji¹,Kobayashi Tetsunori¹,Watanabe Shinji²

Affiliation:

1. Waseda University,Japan

2. Carnegie Mellon University,USA

Funder

ACT-X

Publisher

IEEE

Link

Reference43 articles.

2. bert-base-uncased,0

3. A context-aware knowledge transferring strategy for CTC-based ASR;lu;Proc SLT,2022

Cited by 5 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. 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

2. Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-Based ASR;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Mask-Conformer: Augmenting Conformer with Mask-Predict Decoder;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16

4. Cross-Modal Alignment With Optimal Transport For CTC-Based ASR;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16