Presentation 2018-12-10
[Invited Talk] Review of Automatic Speech Recognition Methodology
Tatsuya Kawahara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The methodology of speech recognition has been changing due to the introduction of deep learning, in particular end-to-end modeling. This article gives a brief overview of the conventional methodologies leading to the end-to-end models. Word-based end-to-end model, referred to as acoustic-to-word model, directly converts a sequence of acoustic features into a word sequence. This model contains acoustic and language models, and does not require a pronunciation lexicon and a complex decoding program. The problems of this new promising model and current solutions are also described.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech Recognition / End-to-End Model / Acoustic-to-Word Model
Paper # SP2018-48
Date of Issue 2018-12-03 (SP)

Conference Information
Committee NLC / IPSJ-NL / SP / IPSJ-SLP
Conference Date 2018/12/10(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Waseda Univ. Nishiwaseda Campus
Topics (in Japanese) (See Japanese page)
Topics (in English) The 5th Natural Language Processing Symposium & The 20th Spoken Language Symposium
Chair Takeshi Sakaki(Hottolink) / / Yoichi Yamashita(Ritsumeikan Univ.)
Vice Chair Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Kazutaka Shimada(Kyushu Inst. of Tech.) / / Akinobu Ri(Nagoya Inst. of Tech.)
Secretary Mitsuo Yoshida(Ryukoku Univ.) / Kazutaka Shimada(NTT) / / Akinobu Ri(Kyoto Univ.) / (Meijo Univ.)
Assistant Takeshi Kobayakawa(NHK) / Hiroki Sakaji(Univ. of Tokyo) / / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language / Technical Committee on Speech / Special Interest Group on Spoken Language Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Invited Talk] Review of Automatic Speech Recognition Methodology
Sub Title (in English) Outlook of Acoustic-to-Word Model
Keyword(1) Speech Recognition
Keyword(2) End-to-End Model
Keyword(3) Acoustic-to-Word Model
1st Author's Name Tatsuya Kawahara
1st Author's Affiliation Kyoto University(Kyoto Univ.)
Date 2018-12-10
Paper # SP2018-48
Volume (vol) vol.118
Number (no) SP-354
Page pp.pp.25-30(SP),
#Pages 6
Date of Issue 2018-12-03 (SP)