Art

J-GLOBAL ID：202002238955989876   Reference number：20A2051087

Using Dialect Label as Auxiliary Feature for End-to-End Japanese Dialect Speech Recognition

方言ラベルを補助特徴量としたEnd-to-End日本語方言音声認識

Author (4)： IMAIZUMI RYO (東京都大) ,  MASUMURA RYO (NTT) ,  SHIOTA SAYAKA (東京都大) ,  KIYA HITOSHI (東京都大)
Material： 日本音響学会研究発表会講演論文集(CD-ROM)  (日本音響学会講演論文集(CD-ROM))
Volume： 2020  Issue： 秋季  Page： ROMBUNNO.3-2-15  Publication year： Aug. 26, 2020 
JST Material Number： G0381C  ISSN： 1880-7658  Document type： Proceedings
Article type： 短報  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *speech recognition ,  *Japanese ,  spoken language ,  label ,  coder ,  decoder
Semi thesaurus term： encoder ,  end to end ,  decoder ,  speech feature quantity ,  標準語 ,  *dialect ,  方言ラベル ,  *方言認識

JST classification (1)： Pattern recognition  (JE07000S)

Reference (7)：

• S. Watanebe, et al., “Hybrid CTC/attention architecture for end-to-end speech recognition,” IEEE Journal of Selected Topics in Signal Processing, Vol. 11, No. 8, pp. 1240-1253, 2017.
• Y. Zhao, et al., “End-to-end-based tibetan multitask speech recognition,” IEEE Access, Vol 7, pp. 162519-162529, 2019.
• L. Dong, et al., “Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition,” In Proc. ICASSP, pp. 5884-5888, 2018.
• T. Nakatani, “Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration,” In Proc. Interspeech, sep, pp. 1408-1412, 2019.
• R. Masumura, et al., “Sequence-Level Consistency Training for Semi-Supervised End-to-End Automatic Speech Recognition,” In Proc. ICASSP, pp. 7054-7058, 2020.

Terms in the title (5)： 方言 ,  ラベル ,  特徴量 ,  日本語 ,  音声認識