A Study of Transducer Based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies-Reference-Cited by-同舟云学术

A Study of Transducer Based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies

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

Author:

Boyer Florian¹,Shinohara Yusuke²,Ishii Takaaki²,Inaguma Hirofumi³,Watanabe Shinji⁴

Affiliation:

1. Airudit, Speech Lab.

2. Yahoo Japan Corporation

3. Kyoto University

4. Carnegie Mellon University

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9687821/9687855/09688251.pdf?arnumber=9688251

Reference42 articles.

1. Improving RNN-transducer with normalized join-ter network;huang;arxiv 2011 01576 (arXv preprint),2020

2. Self-attention trans-ducers for end-to-end speech recognition;tian;Proceedings of the Conference of the International Speech Communication As-sociation,0

3. Accelerating RNN transducer infer-ence via one-step constrained beam search;kim;arxiv 2011 01576 (arXv preprint),2020

4. Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition

5. Re-thinking the inception architecture for computer vision;szegedy;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,0

Cited by 14 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. Decoupled structure for improved adaptability of end-to-end models;Speech Communication;2024-09

2. Accent-Specific Vector Quantization for Joint Unsupervised and Supervised Training in Accent Robust Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024

4. LV-CTC: Non-Autoregressive ASR With CTC and Latent Variable Models;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16

5. A Token-Wise Beam Search Algorithm for RNN-T;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16