• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2011 Fiscal Year Final Research Report

Advancement of speech recognition technology using WFST

Research Project

  • PDF
Project/Area Number 21300062
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Perception information processing/Intelligent robotics
Research InstitutionTokyo Institute of Technology

Principal Investigator

FURUI Sadaoki  東京工業大学, 名誉教授 (90293076)

Co-Investigator(Kenkyū-buntansha) SHINODA Koichi  東京工業大学, 大学院・情報理工学研究科, 准教授 (10343097)
SHINOZAKI Takahiro  千葉大学, 大学院・融合科学研究科, 助教 (80447903)
Project Period (FY) 2009 – 2011
Keywords音声情報処理 / 音声認識 / WFST / デコーダ
Research Abstract

With the aim of improving the performance of automatic speech recognition using the Weighted Finite State Transducer(WFST)-based decoder and developing new applications of the decoder, a wide range of research has been conducted and various achievements have been obtained. The world highest performance speech recognition decoder,"T^3 decoder", has been developed by improving the on-the-fly algorithm for the WFST decoder. Recognition performance under noisy environment has been improved by incorporating speech/non-speech information to the decoder. Various new techniques have been developed to apply the decoder to the recognition of resource-deficient languages and code-switching speech, and to transliteration. Innovative ideas have been proposed toward new directions of the decoder technology. T^3 decoder has been released to domestic as well as overseas research laboratories.

  • Research Products

    (27 results)

All 2012 2011 2010 2009 Other

All Journal Article (8 results) (of which Peer Reviewed: 5 results) Presentation (17 results) Book (1 results) Remarks (1 results)

  • [Journal Article] 軽量な画像特徴量を用いたマルチモーダル音声認識2012

    • Author(s)
      吉川正祥、篠崎隆宏、岩野公司、古井貞煕
    • Journal Title

      電子情報通信学会論文誌

      Volume: Vol.J95-D Pages: 618-627

    • Peer Reviewed
  • [Journal Article] Committee-based active learning for speech recognition2011

    • Author(s)
      Yuzo Hamanaka, Koichi Shinoda, Takuya Tsutaoka, Sadaoki Furui, Tadashi Emori, Takafumi Koshinaka
    • Journal Title

      電子情報通信学会英文論文誌

      Volume: Vol.E94-D Pages: 2015-2023

    • Peer Reviewed
  • [Journal Article] A new hybrid method for machine transliteration2010

    • Author(s)
      D. Yang, P. Dixon, S. Furui
    • Journal Title

      電子情報通信学会論文誌

      Volume: Vol.E93-D Pages: 3377-3383

    • Peer Reviewed
  • [Journal Article] WFSTに基づくT^3デコーダ2010

    • Author(s)
      大西翼、ディクソン・ポール、古井貞煕
    • Journal Title

      情報処理

      Volume: Vol.51 Pages: 1440-1448

  • [Journal Article] 音声認識技術の実用化への取組み2010

    • Author(s)
      古井貞煕
    • Journal Title

      情報処理

      Volume: Vol.5 Pages: 1387-1393

  • [Journal Article] 音声認識実用化技術の展開2010

    • Author(s)
      古井貞煕、小林哲則、矢頭隆、大淵康成、河村聡典、三木清一、庄境誠
    • Journal Title

      電子情報通信学会誌

      Volume: Vol.93 Pages: 725-740

  • [Journal Article] Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition2009

    • Author(s)
      P. Dixon, T. Oonishi, S. Furui
    • Journal Title

      Computer Speech and Language

      Volume: Vol.1 Pages: 510-526

    • Peer Reviewed
  • [Journal Article] WFST音声認識デコーダにおけるon-the-fly合成の最適化処理2009

    • Author(s)
      大西翼、ディクソン・ポール、岩野公司、古井貞煕
    • Journal Title

      電子情報通信学会論文誌

      Volume: Vol.J92-D Pages: 1026-1035

    • Peer Reviewed
  • [Presentation] Designing text corpus using phone-error distribution for acoustic modeling2011

    • Author(s)
      Hiroko Murakami, Koichi Shinoda, Sadaoki Furui
    • Organizer
      Proc. IEEE ASRU
    • Place of Presentation
      Hawaii(米国)
    • Year and Date
      2011-12-11
  • [Presentation] Compact speech decoder based on pure functional programming2011

    • Author(s)
      Takahiro Shinozaki, Masakazu Sekijima, Shigeki Hagihara, Sadaoki Furui
    • Organizer
      Proc. APSIPA-ASC
    • Place of Presentation
      Xi' an(中国)
    • Year and Date
      2011-10-18
  • [Presentation] Strategies for model training and adaptation based on data dependency control2011

    • Author(s)
      Takahiro Shinozaki, Sadaoki Furui
    • Organizer
      Proc. APSIPA-ASC
    • Place of Presentation
      Xi' an(中国)
    • Year and Date
      2011-10-18
  • [Presentation] Speech processing tools An introduction to interoperability2011

    • Author(s)
      Christoph Draxler, Thomas Altosaar, Sadaoki Furui, Mark Liberman, Peter Wittenburg
    • Organizer
      Proc. INTERSPEECH
    • Place of Presentation
      Florence(イタリア)
    • Year and Date
      2011-08-28
  • [Presentation] コンピュータによる音声認識のこれまでと今後の展望2011

    • Author(s)
      古井貞煕
    • Organizer
      日本音響学会春季研究発表会論文集
    • Place of Presentation
      東京(東京都)
    • Year and Date
      2011-03-09
  • [Presentation] Selected topics from ASR research for Asian languages at Tokyo Tech2010

    • Author(s)
      S. Furui
    • Organizer
      Proc. APSIPA-ASC
    • Place of Presentation
      Singapore(シンガポール)
    • Year and Date
      2010-12-17
  • [Presentation] Automatic speech recognition Where we are, and where we should go-2010

    • Author(s)
      S. Furui
    • Organizer
      Proc. ICALIP
    • Place of Presentation
      Shanghai(中国)
    • Year and Date
      2010-11-23
  • [Presentation] VAD-measure-embedded decoder with online model adaptation2010

    • Author(s)
      T. Oonishi, K. Iwano, S. Furui
    • Organizer
      Proc. INTERSPEECH
    • Place of Presentation
      幕張(千葉県)
    • Year and Date
      2010-09-30
  • [Presentation] An empirical comparison of the T^3, Juicer, HDecode and Sphinx3 decoders2010

    • Author(s)
      J. R. Novak, P. Dixon, S. Furui
    • Organizer
      Proc. INTERSPEECH
    • Place of Presentation
      幕張(千葉県)
    • Year and Date
      2010-09-29
  • [Presentation] Exploring web-browser based runtime engines for creating ubiquitous speech interfaces2010

    • Author(s)
      P. Dixon, S. Furui
    • Organizer
      Proc. INTERSPEECH
    • Place of Presentation
      幕張(千葉県)
    • Year and Date
      2010-09-27
  • [Presentation] Jointly optimizing a two-step conditional random field model for machine transliteration and its fast decoding algorithm2010

    • Author(s)
      D. Yang, P. Dixon, S. Furui
    • Organizer
      Proc. ACL
    • Place of Presentation
      Uppsala(スウェーデン)
    • Year and Date
      2010-07-11
  • [Presentation] Evaluation of a WFST-based ASR system for train timetable information2009

    • Author(s)
      J. Novak. E. Whittaker, S. Furui
    • Organizer
      Proc. APSIPA-ASC
    • Place of Presentation
      札幌(北海道)
    • Year and Date
      2009-10-06
  • [Presentation] Development of a WFST-based speech recognition system for a resource deficient language using machine translation2009

    • Author(s)
      A. Jensson, T. Oonishi, K. Iwano, S. Furui
    • Organizer
      Proc. APSIPA-ASC
    • Place of Presentation
      札幌(北海道)
    • Year and Date
      2009-10-05
  • [Presentation] Recent development of WFST-based speech recognition decoder2009

    • Author(s)
      P. Dixon, T. Oonishi, K. Iwano, S. Furui
    • Organizer
      Proc. APSIPA-ASC
    • Place of Presentation
      札幌(北海道)
    • Year and Date
      2009-10-05
  • [Presentation] Robust speech recognition using VAD-measure-embedded decoder2009

    • Author(s)
      T. Oonishi, P. Dixon, K. Iwano, S. Furui
    • Organizer
      Proc. INTERSPEECH
    • Place of Presentation
      Brighton(英国)
    • Year and Date
      2009-09-09
  • [Presentation] Generalization of specialized on-the-fly composition2009

    • Author(s)
      T. Oonishi, P. Dixon, K. Iwano, S. Furui
    • Organizer
      Proc. ICASSP
    • Place of Presentation
      Taipei(台湾)
    • Year and Date
      2009-04-22
  • [Presentation] Fast acoustic computations using graphics processors2009

    • Author(s)
      T. Oonishi, P. Dixon, S. Furui
    • Organizer
      Proc. ICASSP
    • Place of Presentation
      Taipei(台湾)
    • Year and Date
      2009-04-22
  • [Book] Robust speech recognition in the car environment2011

    • Author(s)
      Agnieszka Betkowska Cavalcante, Koichi Shinoda, Sadaoki Furui
    • Total Pages
      11
    • Publisher
      LTC 2009, LNAI 6562, Springer
  • [Remarks]

    • URL

      http://www.furui.cs.titech.ac.jp/top_e.html

URL: 

Published: 2013-07-31  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi