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

Takaaki Hori, Shinji Watanabe, John R. Hershey

研究成果: Conference contribution

75 被引用数 (Scopus)

抄録

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 a 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.

本文言語English
ホスト出版物のタイトルACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
出版社Association for Computational Linguistics (ACL)
ページ518-529
ページ数12
ISBN(電子版)9781945626753
DOI
出版ステータスPublished - 2017
外部発表はい
イベント55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
継続期間: 2017 7月 302017 8月 4

出版物シリーズ

名前ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
1

Other

Other55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
国/地域Canada
CityVancouver
Period17/7/3017/8/4

ASJC Scopus subject areas

  • 言語および言語学
  • 人工知能
  • ソフトウェア
  • 言語学および言語

フィンガープリント

「Joint CTC/attention decoding for end-to-end speech recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル