Joint CTC/attention decoding for end-to-end speech recognition

Takaaki Hori, Shinji Watanabe, John Hershey


Abstract
End-to-end automatic speech recognition (ASR) has become a popular alternative to conventional DNN/HMM systems because it avoids the need for linguistic resources such as pronunciation dictionary, tokenization, and context-dependency trees, leading to a greatly simplified model-building process. There are two major types of end-to-end architectures for ASR: attention-based methods use an attention mechanism to perform alignment between acoustic frames and recognized symbols, and connectionist temporal classification (CTC), uses Markov assumptions to efficiently solve sequential problems by dynamic programming. This paper proposes joint decoding algorithm for end-to-end ASR with a hybrid CTC/attention architecture, which effectively utilizes both advantages in decoding. We have applied the proposed method to two ASR benchmarks (spontaneous Japanese and Mandarin Chinese), and showing the comparable performance to conventional state-of-the-art DNN/HMM ASR systems without linguistic resources.
Anthology ID:
P17-1048
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
518–529
Language:
URL:
https://aclanthology.org/P17-1048
DOI:
10.18653/v1/P17-1048
Bibkey:
Cite (ACL):
Takaaki Hori, Shinji Watanabe, and John Hershey. 2017. Joint CTC/attention decoding for end-to-end speech recognition. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 518–529, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Joint CTC/attention decoding for end-to-end speech recognition (Hori et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1048.pdf
Video:
 https://aclanthology.org/P17-1048.mp4