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

A study on total optimization of multiple pattern recognition systems using cooperative and adaptive training

Research Project

Project/Area Number 25330207
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Perceptual information processing
Research InstitutionWaseda University

Principal Investigator

Ogawa Tetsuji  早稲田大学, 理工学術院, 准教授 (70386598)

Project Period (FY) 2013-04-01 – 2016-03-31
Project Status Completed (Fiscal Year 2015)
Budget Amount *help
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2014: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2013: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywordsパターン認識 / 性能予測 / 深層学習 / 全体最適化 / 行動モデリング
Outline of Final Research Achievements

Attempts have been made to cooperatively optimize multiple pattern recognition systems, developing a total system efficiently and automatically. Specifically, the clustering technique that is robust against the environmental changes and multistream pattern recognition framework, which cooperatively exploits information yielded from multiple systems, have been developed as the fundamental technologies for adaptively refining the systems to cope with the changes in characteristics of data (e.g., users and surrounding environments of the system).

Report

(4 results)
  • 2015 Annual Research Report   Final Research Report ( PDF )
  • 2014 Research-status Report
  • 2013 Research-status Report
  • Research Products

    (32 results)

All 2016 2015 2014 2013 Other

All Int'l Joint Research (2 results) Journal Article (13 results) (of which Int'l Joint Research: 2 results,  Peer Reviewed: 11 results) Presentation (17 results)

  • [Int'l Joint Research] ジョンズホプキンス大学(米国)

    • Related Report
      2015 Annual Research Report
  • [Int'l Joint Research] ブルノ工科大学(チェコ)

    • Related Report
      2015 Annual Research Report
  • [Journal Article] A sampling-based speaker clustering using utterance-oriented Dirichlet process mixture model and its evaluation on large-scale data2015

    • Author(s)
      Naohiro Tawara, Tetsuji Ogawa, Shinji Watanabe, Atsushi Nakamura, Tetsunori Kobayashi
    • Journal Title

      APSIPA Trans. Signal & Info. Process.

      Volume: 4 Issue: 1

    • DOI

      10.1017/atsip.2015.19

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Uncertainty estimation of DNN classifiers2015

    • Author(s)
      Sri Harish Mallidi, Tetsuji Ogawa, Hynek Hermansky
    • Journal Title

      Proc. ASRU2015

      Volume: 1 Pages: 283-288

    • DOI

      10.1109/asru.2015.7404806

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Bilinear map of filter-bank outputs for DNN-based speech recognition2015

    • Author(s)
      Tetsuji Ogawa, Kenshiro Ueda, Kouichi Katsurada, Tetsunori Kobayashi, Tsuneo Nitta
    • Journal Title

      Proc. INTERSPEECH2015

      Volume: 1 Pages: 16-20

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Autoencoder based multi-stream combination for noise robust speech recognition2015

    • Author(s)
      Sri Harish Mallidi, Tetsuji Ogawa, Karel Vesely, Phani Nidadavolu, Hynek Hermansky
    • Journal Title

      Proc. INTERSPEECH2015

      Volume: 1 Pages: 3551-3555

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Blind source separation using associative memory model and linear separation filter2015

    • Author(s)
      Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi, Masaru Fujieda, Kazuhiro Katagiri
    • Journal Title

      Proc. EUSIPCO2015

      Volume: 1 Pages: 1103-1107

    • Related Report
      2015 Annual Research Report
    • Peer Reviewed
  • [Journal Article] A comparative study of spectral clustering for i-vector-based speaker clustering under noisy conditions2015

    • Author(s)
      Naohiro Tawara, Tetsuji Ogawa, Tetsunori Kobayashi
    • Journal Title

      Proc. ICASSP2015

      Volume: 1 Pages: 2041-2045

    • Related Report
      2014 Research-status Report
    • Peer Reviewed
  • [Journal Article] Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial workshop2015

    • Author(s)
      Hynek Hermansky, Lukas Burget, Jordan Cohen, Emmanuel Dupoux Naomi Feldman, John Godfrey, Sanjeev Khudanpur, Matthew Maciejewski, Sri Harish Mallidi, Anjali Menon, Tetsuji Ogawa, Vijayaditya Peddinti, Richard Rose, Richard Stern, Matthew Wiesner, Karel Vesely
    • Journal Title

      Proc. ICASSP2015

      Volume: 1 Pages: 5009-5013

    • Related Report
      2014 Research-status Report
    • Peer Reviewed
  • [Journal Article] Effect of frequency weighting on MLP-based speaker canonicalization2014

    • Author(s)
      Yuichi Kubota, Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi, Tsuneo Nitta
    • Journal Title

      Proc. INTERSPEECH2014

      Volume: 1 Pages: 2987-2991

    • Related Report
      2014 Research-status Report
    • Peer Reviewed
  • [Journal Article] i-vectorを用いた話者認識2014

    • Author(s)
      小川哲司,塩田さやか
    • Journal Title

      日本音響学会誌

      Volume: 70 Pages: 332-339

    • NAID

      110009823396

    • Related Report
      2014 Research-status Report 2013 Research-status Report
  • [Journal Article] Integration of MKL-based and i-vector-based speaker verification by short utterances2013

    • Author(s)
      Hideitsu Hino and Tetsuji Ogawa
    • Journal Title

      Proc. ACML2013

      Volume: --

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] Blocked Gibbs sampling based multi-scale mixture model for speaker clustering on noisy data2013

    • Author(s)
      Naohiro Tawara, Tetsuji Ogawa, Shinji Watanabe, Atsushi Nakamura, and Tetsunori Kobayashi
    • Journal Title

      Proc. MLSP2013

      Volume: --

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] Stream selection and integration in multistream ASR using GMM-based performance monitoring2013

    • Author(s)
      Tetsuji Ogawa, Feipeng Li, and Hynek Hermansky
    • Journal Title

      Proc. Interspeech2013

      Volume: -- Pages: 3332-3336

    • Related Report
      2013 Research-status Report
    • Peer Reviewed
  • [Journal Article] 話者認識で用いる機械学習2013

    • Author(s)
      小川哲司,松井知子
    • Journal Title

      日本音響学会誌

      Volume: vol.69, no.7 Pages: 349-356

    • Related Report
      2013 Research-status Report
  • [Presentation] ニューラルネットワークに基づく識別器の不確かさの推定とマルチストリーム音声認識への適用2016

    • Author(s)
      小川哲司,Mallidi Harish,Vesely Karel,Hermansky Hynek
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      横浜
    • Year and Date
      2016-03-09
    • Related Report
      2015 Annual Research Report
  • [Presentation] 高次相関を考慮した音響特徴量のDNNに基づく音声認識での利用2016

    • Author(s)
      小川哲司,小林哲則,新田恒雄
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      横浜
    • Year and Date
      2016-03-09
    • Related Report
      2015 Annual Research Report
  • [Presentation] 連想記憶に基づく線形分離行列推定を用いたタンデム接続型音源分離2016

    • Author(s)
      大町基,小川哲司,小林哲則,藤枝大,片桐一浩
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      横浜
    • Year and Date
      2016-03-09
    • Related Report
      2015 Annual Research Report
  • [Presentation] 国際会議INTERSPEECH2015参加報告2016

    • Author(s)
      浅見太一,大谷大和,小川哲司,木下慶介,倉田岳人,齋藤大輔,塩田さやか,太刀岡勇気,中村静,増村亮,渡部晋治
    • Organizer
      情報処理学会 音声言語情報処理研究会
    • Place of Presentation
      富山
    • Year and Date
      2016-02-05
    • Related Report
      2015 Annual Research Report
  • [Presentation] 複数の文脈長を考慮したリカレントニューラルネットワークに基づく言語モデル2015

    • Author(s)
      森岡幹,俵直弘,小川哲司,岩田具治,小川厚徳,堀貴明,小林哲則
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      会津若松
    • Year and Date
      2015-09-16
    • Related Report
      2015 Annual Research Report
  • [Presentation] 連想記憶に基づくブラインド音源分離のエコーキャンセリングへの応用2015

    • Author(s)
      大町基, 小川哲司, 小林哲則, 藤枝大, 片桐一浩
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      会津若松
    • Year and Date
      2015-09-16
    • Related Report
      2015 Annual Research Report
  • [Presentation] スペクトラルクラスタリングに基づく話者クラスタリングのための因子分析法の効果の検証2015

    • Author(s)
      俵直弘,小川哲司,小林哲則
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      会津若松
    • Year and Date
      2015-09-16
    • Related Report
      2015 Annual Research Report
  • [Presentation] 国際会議ICASSP2015参加報告2015

    • Author(s)
      岡本拓磨,小川哲司,落合翼,柏木陽佑,亀岡弘和,木下慶介,郡山知樹,齋藤大輔,篠崎隆宏,高木信二,滝口哲也,太刀岡勇気,俵直弘,橋本佳,藤本雅清,松田繁樹,三村正人,吉岡拓也,渡部晋治
    • Organizer
      情報処理学会 音声言語情報処理研究会
    • Place of Presentation
      長野
    • Year and Date
      2015-07-16
    • Related Report
      2015 Annual Research Report
  • [Presentation] テンソル積による基底変換に基づく音声認識に関する研究2015

    • Author(s)
      上田賢次郎,小川哲司,小林哲則,桂田浩一,新田恒雄
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      東京都文京区
    • Year and Date
      2015-03-16 – 2015-03-18
    • Related Report
      2014 Research-status Report
  • [Presentation] 連想記憶と線形分離フィルタを用いたブラインド音源分離2015

    • Author(s)
      大町基,小川哲司,小林哲則,藤枝大,片桐一浩
    • Organizer
      音声言語情報処理研究会
    • Place of Presentation
      三重県志摩市
    • Year and Date
      2015-02-27 – 2015-02-28
    • Related Report
      2014 Research-status Report
  • [Presentation] i-vectorを用いたスペクトラルクラスタリングによる雑音環境下話者クラスタリング2015

    • Author(s)
      俵直弘,小川哲司,小林哲則
    • Organizer
      音声言語情報処理研究会
    • Place of Presentation
      三重県志摩市
    • Year and Date
      2015-02-27 – 2015-02-28
    • Related Report
      2014 Research-status Report
  • [Presentation] 国際会議INTERSPEECH2014,SLT2014参加報告2015

    • Author(s)
      浅見太一,岩野公司,小川哲司,駒谷和範,齋藤大輔,篠田浩一,太刀岡勇気,東中竜一郎,福田隆,増村亮,渡部晋治
    • Organizer
      音声言語情報処理研究会
    • Place of Presentation
      三重県志摩市
    • Year and Date
      2015-02-27 – 2015-02-28
    • Related Report
      2014 Research-status Report
  • [Presentation] スペクトラルクラスタリングに基づく雑音環境下話者クラスタリング2014

    • Author(s)
      俵直弘,小川哲司,小林哲則
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      北海道札幌市
    • Year and Date
      2014-09-03 – 2014-09-05
    • Related Report
      2014 Research-status Report
  • [Presentation] MLPを用いた話者正準化に基づく音声認識の検討2014

    • Author(s)
      久保田雄一,大町基,小川哲司,小林哲則,新田恒雄
    • Organizer
      音声言語情報処理研究会
    • Place of Presentation
      岩手県花巻市
    • Year and Date
      2014-07-24 – 2014-07-26
    • Related Report
      2014 Research-status Report
  • [Presentation] 標準話者母音スペクトルへの変換に基づく話者正準化2014

    • Author(s)
      久保田雄一,大町基,小川哲司,小林哲則,新田恒雄
    • Organizer
      日本音響学会春季研究発表会
    • Place of Presentation
      日本大学理工学部(東京都千代田区)
    • Related Report
      2013 Research-status Report
  • [Presentation] 効率的なサンプリング手法を用いた話者モデリング2013

    • Author(s)
      俵直弘,小川哲司,渡部晋治,中村篤,小林哲則
    • Organizer
      情報処理学会音声言語情報処理研究会
    • Place of Presentation
      遠刈田温泉壮鳳(宮城県刈田郡)
    • Related Report
      2013 Research-status Report
  • [Presentation] 因子分析モデルに基づく話者照合の環境変動に対する頑健性の調査2013

    • Author(s)
      福地佑介, 俵直弘, 小川哲司, 小林哲則
    • Organizer
      日本音響学会秋季研究発表会
    • Place of Presentation
      豊橋技術科学大学(愛知県豊橋市)
    • Related Report
      2013 Research-status Report

URL: 

Published: 2014-07-25   Modified: 2022-02-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi