Kosaka Tetsuo 小坂哲夫

… Alternative Names

KOSAKA Tetsuo 小坂哲夫

Less

Researcher Number	50359569
Other IDs
External Links
Affiliation (Current)	2025: 山形大学, 大学院理工学研究科, 教授
Affiliation (based on the past Project Information) *help	2016 – 2023: 山形大学, 大学院理工学研究科, 教授 2012 – 2015: 山形大学, 理工学研究科, 教授 2012: 山形大学, 大学院・理工学研究科, 教授 2010 – 2011: 山形大学, 大学院・理工学研究科, 准教授 2007: Yamagata University, Graduate School of Science and Engineering, Associate Professor 2003 – 2006: 山形大学, 工学部, 助教授
Review Section/Research Field	Principal Investigator Basic Section 61010:Perceptual information processing-related / Perceptual information processing / Perception information processing/Intelligent robotics Except Principal Investigator Perception information processing/Intelligent robotics
Keywords	Principal Investigator 音声認識 / 音響モデル / 話者適応 / 言語モデル適応 / 音声感情認識 / 深層学習 / ディープラーニング / 感情音声 / ディープニューラルネットワーク / 隠れマルコフモデル … More / 言語モデル / 話し言葉 / 転移学習 / 感情音声コーパス / 自発対話音声 / 音響特徴 / 言語特徴 / 音響モデル適応 / 非言語情報 / 言語情報 / 音声対話システム / 感情認識 / ニューラルネットワーク / 感情音声認識 / 音声区間検出 / 適応技術 / histogram equalization / codebook normalization / MAP estimation / discrete HMM / hidden Markov model / acoustic model / noise / speech recognition / モバイル環境 / 分散音声認識 / コードブック / ケプストラム / 離散混合分布HMM / 耐雑音性 / ヒストグラム同等化 / コードブック正規化 / MAP推定 / 離散分布HMM / 雑音 / 音声コーパス / 話者 / ディープニューラルネット / クラスタリング / 話者クラス音響モデル / 音素環境依存モデル / クロス適応 / 話者ベクトル / 話者インデキシング / クロスバリデーション / 単語グラフ統合 / 教師無し話者適応 / 話し言葉音声認識 … More Except Principal Investigator Unsupervised adaptation / Language model / Acoustic model / Robust speech recognition / Corpus of Spontaneous Japanese / 音声認識 / 離散混合分布HMM / 混合連続分布HMM / 教師なし適応 / 言語モデル / 音響モデル / ロバスト音声認識 / 日本語話し言葉コーパス / System integration / Speech recognition / システム統合 / Discrete-mixture HMM / Continuous-mixture HMM / Spontaneous speech recognition / 品詞N-gram / MLLR / 発音変形依存モデル / 話し言葉音声認識 Less

Development of emotion recognition system by transfer learning for various speechesPrincipal Investigator
- Principal Investigator
  
  小坂哲夫
- Project Period (FY)
  2022 – 2024
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Review Section
  
  Basic Section 61010:Perceptual information processing-related
- Research Institution
  Yamagata University
Emotion detection from speech using high-accuracy emotional speech recognitionPrincipal Investigator
- Principal Investigator
  
  Kosaka Tetsuo
- Project Period (FY)
  2019 – 2021
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Review Section
  
  Basic Section 61010:Perceptual information processing-related
- Research Institution
  Yamagata University
A study on acoustic model adaptation for deep-learning-based speech recognitionPrincipal Investigator
- Principal Investigator
  
  Kosaka Tetsuo
- Project Period (FY)
  2016 – 2018
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perceptual information processing
- Research Institution
  Yamagata University
Automatic classification of speech and audio signals using large-scale corpus and its application to speech recognitionPrincipal Investigator
- Principal Investigator
  
  Kosaka Tetsuo
- Project Period (FY)
  2013 – 2015
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perceptual information processing
- Research Institution
  Yamagata University
Development of high-accuracy system for recognizing spontaneous speechPrincipal Investigator
- Principal Investigator
  
  KOSAKA Tetsuo
- Project Period (FY)
  2010 – 2012
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Yamagata University
Large-vocabulary continuous speech recognition on spontaneous speech task
- Principal Investigator
  
  KOHDA Masaki
- Project Period (FY)
  2006 – 2007
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Yamagata University
Development of Noise Robust Speech Recognition and Its Application on Mobile EnvironmentPrincipal Investigator
- Principal Investigator
  
  KOSAKA Tetsuo
- Project Period (FY)
  2004 – 2006
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Yamagata University
Spontaneous speech recognition
- Principal Investigator
  
  KOHDA Masaki
- Project Period (FY)
  2003 – 2005
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Perception information processing/Intelligent robotics
- Research Institution
  Yamagata University

[Book] 進化するヒトと機械の音声コミュニケーション第1編2章2015
- Author(s)
  小坂哲夫
- Total Pages
  10
- Publisher
  (株)ニッケイ印刷
- Data Source
  KAKENHI-PROJECT-25330183
[Book] "Improvement of Lecture Speech Recognition by Using Unsupervised Adaptation," E-Activity and IntelligentWeb Construction: Effects of Social Design2011
- Author(s)
  Tetsuo Kosaka, Takashi Kusama, Masaharu Kato and Masaki Kohda(T.Matsuo and T.Fujimoto ed.)
- Publisher
  Information Science Reference
- Data Source
  KAKENHI-PROJECT-22500144
[Book] 電子情報通信学会知識ベース ,2群画像・音・言語,7編音声認識と合成 ,「2-4話者・環境適応」(原島博, 他編)2011
- Author(s)
  小坂哲夫
- Total Pages
  3
- Publisher
  電子情報通信学会
- Data Source
  KAKENHI-PROJECT-22500144
[Book] Robust Speech Recognition and Understanding2007
- Author(s)
  T., Kosaka (分担執筆)
- Publisher
  I-Tech
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Book] Robust Speech Recognition and Understanding2007
- Author(s)
  T. Kosaka(分担執筆)
- Total Pages
  18
- Publisher
  I-Tech
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] Simultaneous Adaptation of Acoustic and Language Models for Emotional Speech Recognition Using Tweet Data2024
- Author(s)
  T.kosaka, K.Saeki, Y.Aizawa, M.Kato, T.Nose
- Journal Title
  
  IEICE Trans. Inf. & Syst.
  
  Volume: E107.D Issue: 3 Pages: 363-373
- DOI
  10.1587/transinf.2023HCP0010
- ISSN
  0916-8532, 1745-1361
- Year and Date
  2024-03-01
- Language
  English
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-22K12087
[Journal Article] Speech Emotion Recognition by Late Fusion of Linguistic and Acoustic Features using Deep Learning Models2023
- Author(s)
  K.Sato, K.Kishi, T.Kosaka
- Journal Title
  
  Proc. of APSIPA-ASC2023
  
  Volume: - Pages: 1013-1018
- DOI
  10.1109/apsipaasc58517.2023.10317325
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-22K12087
[Journal Article] Emotion Recognition Combining Acoustic and Linguistic Features Based on Speech Recognition Results2021
- Author(s)
  Misaki Sakurai, Tetsuo Kosaka
- Journal Title
  
  Proc. of 2021 IEEE 10th Global Conference on Consumer Electronics
  
  Volume: - Pages: 889-892
- DOI
  10.1109/gcce53005.2021.9621810
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19K12014
[Journal Article] Language model adaptation for emotional speech recognition using Tweet data2020
- Author(s)
  Kazuya Saeki, Masaharu Kato, Tetsuo Kosaka
- Journal Title
  
  Proc, APSIPA Annual Summit and Conference 2020
  
  Volume: - Pages: 371-375
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19K12014
[Journal Article] Performance Improvement of Prosody-Controlled Voice Conversion by Language Model Adaptation2019
- Author(s)
  Kazuya Saeki, Masaharu Kato, Tetsuo Kosaka
- Journal Title
  
  Proc. of the 8th global conference on consumer electronics
  
  Volume: 1 Pages: 1-3
- DOI
  10.1109/gcce46687.2019.9015444
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-19K12014
[Journal Article] Investigation of acoustic models for emotion recognition using a spontaneous speech corpus2019
- Author(s)
  Tetsuo Kosaka, Yuka Haneda, Daisuke Makabe, Masaharu Kato
- Journal Title
  
  Proc. of the 23rd International Congress on Acoustics
  
  Volume: 1 Pages: 6795-6800
- Open Access
- Data Source
  KAKENHI-PROJECT-19K12014
[Journal Article] Acoustic Model Adaptation for Emotional Speech Recognition Using Twitter-Based Emotional Speech Corpus2018
- Author(s)
  Kosaka Tetsuo、Aizawa Yoshitaka、Kato Masaharu、Nose Takashi
- Journal Title
  
  Proc. of APSIPA ASC 2018
  
  Volume: - Pages: 1747-1751
- DOI
  10.23919/apsipa.2018.8659756
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16K00227
[Journal Article] Unsupervised Cross Adaptation Using Deep Neural Networks in Speech Recognition Systems2018
- Author(s)
  冨田健斗、高木瑛、加藤正治、小坂哲夫
- Journal Title
  
  電子情報通信学会論文誌D 情報・システム
  
  Volume: J101-D Issue: 8 Pages: 1190-1199
- DOI
  10.14923/transinfj.2017JDP7076
- ISSN
  1880-4535, 1881-0225
- Year and Date
  2018-08-01
- Language
  Japanese
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16K00227
[Journal Article] Improving Voice Activity Detection for Multimodal Movie Dialogue Corpus2018
- Author(s)
  Kosaka Tetsuo、Suga Ikumi、Inoue Masashi
- Journal Title
  
  2018 IEEE 7th Global Conference on Consumer Electronics (GCCE)
  
  Volume: - Pages: 481-484
- DOI
  10.1109/gcce.2018.8574730
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16K00202, KAKENHI-PROJECT-16K00227
[Journal Article] Large-scale multimodal movie dialogue corpus2016
- Author(s)
  Ryu Yasuhara, Masashi Inoue, Ikumi Suga and Tetsuo Kosaka
- Journal Title
  
  Proc. of the 18th ACM International Conference on Multimodal Interaction
  
  Volume: - Pages: 414-415
- DOI
  10.1145/2993148.2998523
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16K00227
[Journal Article] Voice activity detection in movies using multi-class deep neural networks2016
- Author(s)
  I. Suga, R. Yasuhara, M. Inoue and T. Kosaka
- Journal Title
  
  The Journal of the Acoustical Society of America
  
  Volume: 140 Issue: 4_Supplement Pages: 3116-3116
- DOI
  10.1121/1.4969758
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16K00227
[Journal Article] Many-to-many voice conversion using hidden Markov model-based speech recognition and synthesis2016
- Author(s)
  Y. Aizawa, M. Kato and T. Kosaka
- Journal Title
  
  The Journal of the Acoustical Society of America
  
  Volume: 140 Issue: 4_Supplement Pages: 2964-2964
- DOI
  10.1121/1.4969167
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16K00227
[Journal Article] Deep Neural Network-Based Speech Recognition with Combination of Speaker-Class Models2015
- Author(s)
  Tetsuo Kosaka, Kazuki Konno, Masaharu Kato
- Journal Title
  
  Proc. of APSIPA ASC 2015
  
  Volume: SP2-2.3 Pages: 1-4
- DOI
  10.1109/apsipa.2015.7415464
- Peer Reviewed / Acknowledgement Compliant / Open Access
- Data Source
  KAKENHI-PROJECT-25330183
[Journal Article] Unsupervised cross-adaptation using language model and deep learning based acoustic model adaptations2014
- Author(s)
  Akira Takagi, Kazuki Konno, Masaharu Kato and Tetsuo Kosaka
- Journal Title
  
  Proc. of APSIPA ASC 2014
  
  Volume: WA-P-16 Pages: 1-4
- DOI
  10.1109/apsipa.2014.7041581
- Peer Reviewed / Acknowledgement Compliant / Open Access
- Data Source
  KAKENHI-PROJECT-25330183
[Journal Article] A time-synchronous histogram equalization for noise robust speech recognition2013
- Author(s)
  Fumiya Takahashi, Masaharu Kato and Tetsuo Kosaka
- Journal Title
  
  Proc. of ICA
  
  Volume: 採録決定 Pages: 5-5
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] 識別学習を用いた離散混合分布HMMによる音声認識2013
- Author(s)
  小坂哲夫，加藤正治
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 54 Pages: 436-442
- NAID
  110009537036
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] 識別学習を用いた離散混合分布 HMMによる音声認識2013
- Author(s)
  小坂哲夫,加藤正治
- Journal Title
  
  情報処理学会論文誌
  
  Volume: Vol. 54 No. 2 Pages: 436-442
- NAID
  110009537036
- URL
  https://ipsj.ixsq.nii.ac.jp/ej/index.php?active_action=repository_view_main_item_detail&item_id=90262&item_no=1&page_id=13&block_id=8
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] An investigation of vowel substitution rules in the automatic evaluation system of English pronunciation2013
- Author(s)
  Kei Sato, Masaharu Kato and Tetsuo Kosaka
- Journal Title
  
  Proc. of ICA
  
  Volume: 採録決定 Pages: 5-5
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] A time-synchronous histogram equalization for noise robust speech recognition2013
- Author(s)
  Fumiya Takahashi, Masaharu Kato and Tetsuo Kosaka
- Journal Title
  
  Proc. of International Congress on Acoustics 2013
  
  Volume: 1 Pages: 1-5
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Speech recognition with large-scale speaker-class-based acoustic modeling2013
- Author(s)
  Kazuki Konno, Masaharu Kato and Tetsuo Kosaka
- Journal Title
  
  Proc. of APSIPA ASC 2013
  
  Volume: OS.28-SLA..9, 113 Pages: 1-4
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330183
[Journal Article] An investigation of vowel substitution rules in the automatic evaluation system of English pronunciation2013
- Author(s)
  Kei Sato, Masaharu Kato and Tetsuo Kosaka
- Journal Title
  
  Proc. of International Congress on Acoustics 2013
  
  Volume: 1 Pages: 1-5
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] 話者クラス音響モデル及び単語グラフ統合を用いた音声認識2013
- Author(s)
  小坂哲夫，伊藤貴，加藤正治，好田正紀
- Journal Title
  
  電子情報通信学会論文誌,
  
  Volume: Vol. J96-D, No. 11 Pages: 2795-2803
- NAID
  110009661670
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330183
[Journal Article] Unsupervised Cross-Adaptation Approach for Speech Recognition by Combined Language Model and Acoustic Model Adaptation2011
- Author(s)
  Tetsuo Kosaka, Taro Miyamoto, Masaharu Kato
- Journal Title
  
  Proc.of APSIPA ASC 2011
  
  Volume: (CD-ROM)
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Speaker Vector-Based Verification by Phonetic Class-Based Modeling2011
- Author(s)
  Tetsuo Kosaka, Naoki Tadokoro, Masaharu Kato and Masaki Kohda
- Journal Title
  
  Journal of Information Assurance and Security
  
  Volume: Vol. 6, No.3 Pages: 186-194
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Lecture Speech Recognition Using Discrete-Mixture HMMs2011
- Author(s)
  Tetsuo Kosaka, Akiyoshi Yamamoto, Takuya Kumakura, Masaharu Kato, Masaki Kohda
- Journal Title
  
  IEEJ Transactions on Electrical and Electromc Engineering
  
  Volume: Vol.6, No.1 Pages: 23-29
- NAID
  10027629753
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Unsupervised Cross-Adaptation Approach for Speech Recognition by Combined Language Model and Acoustic Model Adaptation2011
- Author(s)
  Tetsuo Kosaka, Taro Miyamoto and Masaharu Kato
- Journal Title
  
  Proc. of APSIPA ASC 2011, Thu-PM
  
  Pages: 4-4
- URL
  http://www.apsipa.org/proceedings_2011/pdf/APSIPA177.pdf
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Lecture Speech Recognition Using Discrete-Mixture HMMs2011
- Author(s)
  Tetsuo Kosaka, Akiyoshi Yamamoto, Takuya Kumakura, Masaharu Kato and Masaki Kohda
- Journal Title
  
  IEEJ Transactions on Electrical and Electronic Engineering
  
  Volume: Vol. 6 No. 1 Issue: 1 Pages: 23-29
- DOI
  10.1002/tee.20602
- NAID
  10027629753
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Speaker Vector-Based Verification by Phonetic Class-Based Modeling2011
- Author(s)
  Tetsuo Kosaka, Naoki Tadokoro, Masaharu Kato, Masaki Kohda
- Journal Title
  
  Journal of Information Assurance and Security
  
  Volume: Vo1.6, No.3 Pages: 186-194
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Performance Improvement in Automatic Evaluation System of English Pronunciation by Using Various Normalization Methods2010
- Author(s)
  Masaru Kusumi, Masaharu Kato, Tetsuo Kosaka and Itaru Matsunaga
- Journal Title
  
  Proc. of International Congress on Acoustics 2010
  
  Volume: 257 Pages: 6-6
- URL
  http://www.acoustics.asn.au/conference_proceedings/ICA2010/cdrom-ICA2010/papers/p257.pdf
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Speaker Adaptation Based on System Combination Using Speaker-Class Models2010
- Author(s)
  Tetsuo Kosaka, Takashi Ito, Masaharu Kato and Masaki Kohda
- Journal Title
  
  Proc. of Interspeech2010
  
  Pages: 546-549
- URL
  http://www.isca-speech.org/archive/interspeech_2010/i10_0546.html
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Lecture Speech Recognition by Combining Word Graphs of Various Acoustic Models2010
- Author(s)
  Tetsuo Kosaka, Keisuke Goto, Takashi Ito and Masaharu Kato
- Journal Title
  
  Proc. of Interspeech2010
  
  Pages: 2978-2981
- URL
  http://www.isca-speech.org/archive/interspeech_2010/i10_2978.html
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Unsupervised Speaker Adaptation Using Speaker-Class Models for Lecture Speech Recognition2010
- Author(s)
  Tetsuo Kosaka, Yuui Takeda, Takashi Ito, Masaharu Kato, Masaki Kohda
- Journal Title
  
  IEICE Transactions on Information and Systems
  
  Volume: Vo1.E93-D, No.9 Pages: 2363-2369
- NAID
  10027640196
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Quinphone HM-netを用いた単語グラフ統合に基づく講演音声認識2010
- Author(s)
  加藤正治, 小坂哲夫, 伊藤彰則, 牧野正三
- Journal Title
  
  電子情報通信学会技術研究報告
  
  Volume: SP2010-28 Pages: 37-42
- NAID
  110007969989
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Speech Recognition in Noise by Using Word Graph Combinations2010
- Author(s)
  Shunsuke Kuramata, MasaharuKato, Tetsuo Kosaka
- Journal Title
  
  Proc.of International Congress on Acoustics 2010
  
  Volume: CD-ROM
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Speech Recognition in Noise by Using Word Graph Combinations2010
- Author(s)
  Shunsuke Kuramata, Masaharu Kato and Tetsuo Kosaka
- Journal Title
  
  Proc. of International Congress on Acoustics 2010
  
  Volume: 341 Pages: 6-6
- URL
  http://www.acoustics.asn.au/conference_proceedings/ICA2010/cdrom-ICA2010/papers/p341.pdf
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] 単語グラフ統合を用いた種々の雑音環境下での音声認識2010
- Author(s)
  倉又俊輔, 加藤正治, 小坂哲夫
- Journal Title
  
  電子情報通信学会技術研究報告
  
  Volume: SP2010-41 Pages: 37-42
- NAID
  110007890249
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Lecture Speech Recognition by Combining Word Graphs of Various Acoustic Models2010
- Author(s)
  Tetsuo Kosaka, Keisuke Goto, Takashi Ito, Masaharu Kato
- Journal Title
  
  Proc.of Interspeech2010
  
  Volume: CD-ROM Pages: 2978-2981
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Speaker Adaptation Based on System Combination Using Speaker-Class Models2010
- Author(s)
  Tetsuo Kosaka, Takashi Ito, Masaharu Kato, Masaki Kohda
- Journal Title
  
  Proc.of Interspeech2010
  
  Volume: CD-ROM Pages: 546-549
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22500144
[Journal Article] Histogram equalization for noise robust speech recognition by using discrete-mixture HMMs2008
- Author(s)
  T. Kosaka
- Journal Title
  
  Acoustical Science and Technology 29
  
  Pages: 66-73
- NAID
  110006533631
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] Histogram equalization for noise robust speech recognition using discrete-mixture HMMs2008
- Author(s)
  T. Kosaka, M. Katoh, M. Kohda
- Journal Title
  
  Acoustical Science and Technology vol.29, no.1
  
  Pages: 66-73
- NAID
  110006533631
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] Histogram equalization for noise rebust speech recognition using discrete-mixture HMMs2008
- Author(s)
  T., Kosaka
- Journal Title
  
  Acoustical Science and Techmhnology 29
  
  Pages: 66-73
- Description
  「研究成果報告書概要(和文)」より
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] Speaker vector-based speaker identification with phonetic modeling2007
- Author(s)
  T. Kosaka, T. Akatsu, M. Katoh, M. Kohda
- Journal Title
  
  IEICE Trans. on Information and Systems vol.J90-D, no.12
  
  Pages: 3201-3209
- NAID
  110007380643
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] 音素モデルを用いた話者ベクトルに基づく話者識腹2007
- Author(s)
  小坂哲夫
- Journal Title
  
  電子情報帳信学会論文誌D J90-D
  
  Pages: 3201-3209
- Description
  「研究成果報告書概要(和文)」より
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] 発音変形依存モデルを用いた講演音声認識2006
- Author(s)
  堤怜介, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  電子情報通信学会論文誌D Vol.J89-D,No.2
  
  Pages: 305-313
- NAID
  110004669949
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 離散混合分布HMMのヒストグラム同等化を用いたコードブック正規化2006
- Author(s)
  小坂哲夫
- Journal Title
  
  電子情報通信学会技術研究報告 SP2006-15
  
  Pages: 25-30
- NAID
  110004750981
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] Noisy Speech Recognition Based on Codebook Normalization of Discrete-Mixture HMMs2006
- Author(s)
  T.Kosaka
- Journal Title
  
  ASA/ASJ Forth Joint Meeting 1pSC27
  
  Pages: 3041-3041
- Data Source
  KAKENHI-PROJECT-18500126
[Journal Article] 離散混合分布HMMのヒストグラム同等化を用いたコードブック正規化2006
- Author(s)
  小坂哲夫, 加藤正治, 好田正紀
- Journal Title
  
  電子情報通信学会技術研究報告 SP2006-25
  
  Pages: 25-30
- NAID
  110004750981
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 書き起こしと講演録を用いた言語モデルの作成法の検討2006
- Author(s)
  加藤正治, 梅本真模, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 3-1-7
  
  Pages: 1203-1204
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] コードブック適応を用いた離散混合分布型HMMによる講演音声認識2006
- Author(s)
  山本明祥, 熊倉拓哉, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 2-2-9
  
  Pages: 69-70
- NAID
  110004849727
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 音素モデルを用いた話者ベクトルに基づく話者識別の検討2006
- Author(s)
  赤津達也, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  電子情報通信学会技術研究報告 SP2006-101
  
  Pages: 95-99
- NAID
  110006164204
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 参議院会議音声の言語モデル適応2006
- Author(s)
  加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 2-P-29
  
  Pages: 151-152
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 日本語話し言葉コーパスを用いた教師なし適応による講演音声認識の性能改善2006
- Author(s)
  阿部拓也, 草間隆, 武田千春, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 3-1-8
  
  Pages: 1205-1206
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 発音変形依存モデルを用いた講演音声認識2006
- Author(s)
  堤怜介, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  電子情報通信学会論文誌D Vol. J89-D, No.2
  
  Pages: 305-313
- NAID
  110004669949
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Lecture speech recognition using pronunciation variant modeling2006
- Author(s)
  R.Tsutsumi, M.Katoh, T.Kosaka, M.Kohda
- Journal Title
  
  IEICE Transactions on Information and Systems Vol.J89-D, No.2
  
  Pages: 305-313
- NAID
  110004669949
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] Noisy speech recognition based on codebook normalization of discrete-mixture HMMs2006
- Author(s)
  Tetsuo Kosaka, Masaharu Katoh, Masaki Kohda
- Journal Title
  
  ASA/ASJ Forth Joint Meeting 1pSC27
  
  Pages: 3041-3041
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] コードブック適応を用いた離散混合分布型HMMによる講演音声認識2006
- Author(s)
  山本明祥, 熊倉拓哉, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  音声言語情報処理研究報告 2006-SLP-62
  
  Pages: 25-30
- NAID
  110004849727
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Lecture Speech Recognition Using Pronunciation Variant Modeling2006
- Author(s)
  R.Tsutsumi, M.Katoh, T.Kosaka, M.Kohda
- Journal Title
  
  IEICE Transactions D Vol.J89-D, No.2
  
  Pages: 305-313
- NAID
  110004669949
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 話者ベクトルを用いた話者識別法における音響モデルの検討2006
- Author(s)
  赤津達也, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 2-P-10
  
  Pages: 113-114
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Noisy Speech Recognition Based on Codebook Normalization of Discrete-Mixture HMMs2006
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  ASA/ASA Forth Joint Meeting 1pSC27
  
  Pages: 3041-4041
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 話者ベクトルを用いた話者識別法における次元圧縮の効果2006
- Author(s)
  赤津達也, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 1-P-18
  
  Pages: 159-160
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Noisy Speech recognition Based on Codebook Normalization of Discrete-Mixture HMMs2006
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  ASA/ASJ Forth Joint Meeting 1pSC27
  
  Pages: 3041-3041
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 離散混合分布HMMのコードブック正規化による雑音下音声認識2006
- Author(s)
  遠藤大悟, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 3-1-16
  
  Pages: 139-140
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 日本語話し言葉コーパスによる離散混合分布型HMMの評価2005
- Author(s)
  小坂哲夫
- Journal Title
  
  日本音響学会講演論文集(秋季) 2-7-19
  
  Pages: 64-64
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] 日本語話し言葉コーパスによる離散混合分布HMMの評価2005
- Author(s)
  小坂哲夫, 山本明祥, 加藤正治, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 2-7-19
  
  Pages: 95-96
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Robust Speech Recognition Using Discrete-Mixture HMMs2005
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  IEICE Transactions on Information and Systems Vol.E88-D, No.12
  
  Pages: 2811-2818
- NAID
  110004019504
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Robust speech recognition under non-stationary noise using discrete-mixture HMMs2005
- Author(s)
  小坂哲夫
- Journal Title
  
  2005 RISP International Workshop on Nonlinear Circuits and Signal Processing
  
  Pages: 347-350
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] 離散混合出力分布型HMMによる雑音下音声認識のMFCCでの評価2005
- Author(s)
  小坂哲夫
- Journal Title
  
  日本音響学会講演論文集(春季) 3-5-11
  
  Pages: 97-98
- NAID
  10018037199
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] Robust speech recognition under non-stationary noise using discrete-mixture HMMs2005
- Author(s)
  T.Kosaka
- Journal Title
  
  Proc. of International Workshop on Nonlinear Circuit and Signal Processing 1
  
  Pages: 347-350
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] Robust Speech Recognition Using Discrete-Mixture HMMs2005
- Author(s)
  T.Kosaka
- Journal Title
  
  IEICE Transaction on Information and Systems (電子情報通信学会英文論文誌) E88-D,12
  
  Pages: 2811-2818
- NAID
  110004019504
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] Robust speech recognition using discrete-mixture HMMs2005
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  IEICE Transactions on Information and Systems Vol.E88-D, No.12
  
  Pages: 2811-2818
- NAID
  110004019504
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] Robust Speech Recognition under Non-Stationary Noise Using Discrete-Mixture HMMs2005
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  Proc. of 2005 RISP International Workshop on Nonlinear Circuits and Signal Processing
  
  Pages: 347-350
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 離散混合分布型HMMによる講演音声認識の検討2005
- Author(s)
  小坂哲夫
- Journal Title
  
  電子情報通信学会技術研究報告 SP2005-25
  
  Pages: 31-36
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] Robust Speech Recognition Using Discrete-Mixture HMMs2005
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  IEICE Transaction on Information and Systems Vol.E88-D No.12
  
  Pages: 2811-2818
- NAID
  110004019504
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Robust Speech Recognition Using Discrete-Mixture HMMs2005
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  IEICE Transactions on Information and Systems Vol. E88-D No.12
  
  Pages: 2811-2818
- NAID
  110004019504
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 雑音混合出力分布型HMMによる雑音下音声認識のMFCCでの評価2005
- Author(s)
  小坂哲夫, 加藤正治, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 3-5-II
  
  Pages: 97-98
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Rebust Speech Recognition Using Discrete-Mixture HMMs2005
- Author(s)
  小坂哲夫
- Journal Title
  
  IEICE Trans. on Information and Systems(電子情報通信学会英文論文誌) E88-D,12
  
  Pages: 2811-2818
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] 日本語話し言葉コーパスを用いた発音変形依存モデルによる講演音声認識の性能評価2005
- Author(s)
  阿部拓也, 武田千春, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  日本音響学会講演論文集 2-1-1
  
  Pages: 37-38
- NAID
  110003488493
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] 離散混合分布型HMMによる講演音声認識の検討2005
- Author(s)
  小坂哲夫, 山本明祥, 加藤正治, 好田正紀
- Journal Title
  
  電子情報通信学会技術研究報告 SP2005-25
  
  Pages: 31-36
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Robust speech recognition under non-stationary noise using discrete-mixture HMMs2005
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  Proc.of International Workshop on Nonlinear Circuit and Signal Processing
  
  Pages: 347-350
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] 日本語話し言葉コーパスを用いた発音変形依存モデルによる講演音声認識の性能評2005
- Author(s)
  阿部拓也, 草間隆, 武田千春, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  電子情報通信学会技術研究報告 SP2005-94
  
  Pages: 25-30
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Robust Speech Recognition under Non-Stationary Noise Using Discrete-Mixture HMMs2005
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  Proc.of 2005 RISP International Workshop on Nonlinear Circuits and Signal Processing
  
  Pages: 347-350
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Noisy speech recognition with discrete-mixture HMMs based on MAP estimation2004
- Author(s)
  T.Kosaka
- Journal Title
  
  Proc. of The 18th International Congress on Acoustics 2
  
  Pages: 1691-1694
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] Noisy Speech Recognition with Discrete-Mixture HMMs Based on MAP Estimation2004
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  Proc. of The 18th International Congress on Acoustics Vol II
  
  Pages: 1691-1694
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Noisy Speech Recognition with Discrete-Mixture HMMs Based on MAP Estimation2004
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  Proc.of the 18th International Congress on Acoustics Vol.II
  
  Pages: 1691-1694
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Noisy speech recognition with discrete-mixture HMMs based on MAP estimation2004
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  Proc.of The 18th International Congress on Acoustics Vol.II
  
  Pages: 1691-1694
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15500098
[Journal Article] ETSI標準フロントエンドを用いた雑音下音声認識の検討2004
- Author(s)
  福士なな子, 加藤正治, 小坂哲夫, 好田正紀
- Journal Title
  
  電子情報通信学会技術研究報告 SP2004-II
  
  Pages: 7-12
- NAID
  110003295894
- Data Source
  KAKENHI-PROJECT-16500097
[Journal Article] Noisy Speech Recognition with Discrete-Mixture HMMs Based on MAP Estimation2004
- Author(s)
  T.Kosaka, M.Katoh, M.Kohda
- Journal Title
  
  Proc.of The 18th International Congress on Acoustics Vol II
  
  Pages: 1691-1694
- Data Source
  KAKENHI-PROJECT-16500097
[Presentation] 話し言葉を考慮した音響および言語特徴併用による音声感情認識2023
- Author(s)
  岸恵太，佐藤清秀，小坂哲夫
- Organizer
  第258回自然言語処理・第149回音声言語情報処理合同研究発表会
- Data Source
  KAKENHI-PROJECT-22K12087
[Presentation] 話し言葉を考慮した言語特徴による音声感情認識2023
- Author(s)
  岸恵太，佐藤清秀，小坂哲夫
- Organizer
  音響学会秋季研究発表会
- Data Source
  KAKENHI-PROJECT-22K12087
[Presentation] 深層学習モデルを用いた言語特徴と音響特徴の後期融合による音声感情認識2023
- Author(s)
  佐藤清秀，岸恵太，小坂哲夫
- Organizer
  日本音響学会春季研究発表会
- Data Source
  KAKENHI-PROJECT-22K12087
[Presentation] 感情コーパスJTESを用いた時系列情報を考慮した音声感情認識2022
- Author(s)
  須々田和基，櫻井美咲，小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 言語特徴と音響特徴の後期融合による音声感情認識の検討2022
- Author(s)
  佐藤清秀，岸恵太，小坂哲夫
- Organizer
  第５回東北地区音響学研究会
- Data Source
  KAKENHI-PROJECT-22K12087
[Presentation] 音声認識結果による言語特徴と音響特徴による音声感情認識の検討2022
- Author(s)
  櫻井美咲, 須々田和基, 小坂哲夫
- Organizer
  日本音響学会秋季講演論文集
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 音声認識結果に基づく言語特徴と音響特徴による音声感情認識2021
- Author(s)
  櫻井美咲，小坂哲夫
- Organizer
  日本音響学会音声研究会
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] ツイート情報を利用した言語モデルによる感情音声認識2020
- Author(s)
  佐伯和哉，加藤正治，小坂哲夫
- Organizer
  日本音響学会春季講演論文集
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 音声による感情認識における時系列特徴量と統計量の融合方法の検討2020
- Author(s)
  羽田優花，加藤正治，小坂哲夫
- Organizer
  情報処理学会東北支部研究会報告
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 感情音声認識を対象とした言語モデル適応の評価2020
- Author(s)
  佐伯和哉, 加藤正治, 小坂哲夫
- Organizer
  東北地区音響学研究会
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 音声の時系列特徴量と統計量の融合による感情認識2020
- Author(s)
  羽田優花, 櫻井美咲, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会秋季講演論文集
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 感情音声データベースJTESを用いた音声感情認識における特徴量の検討2019
- Author(s)
  羽田優花，加藤正治，小坂哲夫
- Organizer
  日本音響学会秋季講演論文集
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 言語モデルの改良による感情音声の認識と韻律制御声質変換の性能向上2019
- Author(s)
  佐伯和哉，加藤正治，小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] 音響・言語モデルの同時適応による感情音声認識の精度改善2019
- Author(s)
  佐伯和哉，加藤正治，小坂哲夫，能勢隆
- Organizer
  日本音響学会秋季講演論文集
- Data Source
  KAKENHI-PROJECT-19K12014
[Presentation] 日本語感情音声コーパスJTESを対象とした感情認識の基礎検討2019
- Author(s)
  羽田優花，加藤正治，小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] DNNを用いた教師なしクロス適応の性能評価2018
- Author(s)
  冨田建斗，加藤正治，小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] 感情音声認識における音響モデル適応と声質変換への応用2018
- Author(s)
  小坂哲夫，相澤佳孝，加藤正治，能勢隆
- Organizer
  日本音響学会秋季講演論文集
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] 自発対話音声を用いた感情認識の学習データによる検討2018
- Author(s)
  真壁大介，加藤正治，小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] DNNによる音声認識を用いた感情音声の声質変換の検討2017
- Author(s)
  笹田拓臣，相澤佳孝, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] DNNを用いた映画の音声区間検出におけるクラス分類の検討2017
- Author(s)
  菅郁巳，小坂哲夫，井上雅史
- Organizer
  日本音響学会秋季講演論文集
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] 映画からのマルチモーダル対話コーパスの作成2017
- Author(s)
  井上雅史，安原龍，菅郁巳，小坂哲夫
- Organizer
  人工知能学会全国大会
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] 感情音声データベースJTESを用いた感情音声認識におけるモデル適応の性能向上の検討2017
- Author(s)
  相澤佳孝，小坂哲夫，加藤正治，能勢隆
- Organizer
  情報処理学会研究報告
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] 感情音声データベースJTESを用いた感情音声認識におけるDNN-HMM音響モデル適応の検討2017
- Author(s)
  相澤佳孝，小坂哲夫，加藤正治，能勢隆
- Organizer
  日本音響学会秋季講演論文集
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] Voice Conversion of emotional speech using hidden Markov model-based speech recognition and synthesis2016
- Author(s)
  Tetsuo Kosaka, Yoshiaki Nakagawa and Masaharu Kato
- Organizer
  Proc. of 22nd International Congress on Acoustics
- Place of Presentation
  Buenos Aires, Argentina
- Year and Date
  2016-09-05
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] ディープニューラルネットワークを用いた映画中の音声区間検出の検討2016
- Author(s)
  菅郁巳, 安原龍, 井上雅史, 小坂哲夫
- Organizer
  日本音響学会春季講演論文集
- Place of Presentation
  桐蔭横浜大学
- Year and Date
  2016-03-09
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] 高精度な初期モデルを用いた教師なしクロス適応の評価2016
- Author(s)
  冨田健斗, 高木瑛, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会秋季講演論文集
- Place of Presentation
  富山大学
- Year and Date
  2016-09-14
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] HMM認識・合成による感情音声の声質変換の性能向上2016
- Author(s)
  相澤佳孝, 中川由暁, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会秋季講演論文集
- Place of Presentation
  富山大学
- Year and Date
  2016-09-14
- Data Source
  KAKENHI-PROJECT-16K00227
[Presentation] ディープニューラルネットによる話者クラス音響モデルを用いた音声認識2015
- Author(s)
  今野和樹，加藤正治，小坂哲夫
- Organizer
  日本音響学会秋季講演論文集
- Place of Presentation
  会津大学
- Year and Date
  2015-09-16
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] DNN-HMMを用いた音声認識におけるパラメータ数の検討2015
- Author(s)
  小野瑞穂, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Year and Date
  2015-03-04
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] DNN-HMMを用いた日本語講演音声認識における話者適応の検討2014
- Author(s)
  小坂哲夫, 今野和樹, 高木瑛, 加藤正治
- Organizer
  日本音響学会春季講演論文集
- Place of Presentation
  日本大学理工学部
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] 大規模話者クラス音響モデルを用いた音声認識の精度向上の検討2013
- Author(s)
  今野和樹, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  豊橋技術科学大学
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] 単語グラフを用いた音声アライメント2013
- Author(s)
  加藤正治, 小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  豊橋技術科学大学
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] 入力音声の韻律情報を用いたHMM音声合成2013
- Author(s)
  栗原大樹,加藤正治,小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Year and Date
  2013-03-11
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] クロスバリデーションによる教師なし言語適応における各種パラメータの最適化2013
- Author(s)
  高木瑛,加藤正治,小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Year and Date
  2013-03-11
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 雑音下音声認識におけるフレーム重みづけヒストグラム同等化法の検討2012
- Author(s)
  高橋郁也,加藤正治,小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  信州大学
- Year and Date
  2012-09-19
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 単語グラフ統合を用いた残響下音声認識の検討2012
- Author(s)
  倉又俊輔, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  神奈川大学
- Year and Date
  2012-03-13
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 教師なし話者適応における各種パラメータの最適化2012
- Author(s)
  今野聡介,加藤正治,小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Year and Date
  2012-03-09
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 日本人英語の自動発音評定における誤り規則の検討2012
- Author(s)
  佐藤慶,加藤正治,小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  信州大学
- Year and Date
  2012-09-21
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 教師なし話者適応における各種パラメータの最適化2012
- Author(s)
  今野聡介, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学
- Year and Date
  2012-03-09
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 雑音下音声認識におけるヒストグラム同等化法の改良2012
- Author(s)
  高橋郁也, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学
- Year and Date
  2012-03-09
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 自動発音評定における母音置換規則の検討2012
- Author(s)
  佐藤慶,加藤正治,小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Year and Date
  2012-03-09
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 単語グラフ統合を用いた残響下音声認識の検討2012
- Author(s)
  倉又俊輔,加藤正治,小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  神奈川大学横浜キャンパス
- Year and Date
  2012-03-13
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 雑音下音声認識におけるヒストグラム同等化法の改良2012
- Author(s)
  高橋郁也,加藤正治,小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Year and Date
  2012-03-09
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 話者クラス音響モデルを用いた講演音声認識におけるクラスタリング手法の各種検討2012
- Author(s)
  今野和樹,大山拓也,加藤正治,小坂哲夫
- Organizer
  音声言語情報処理研究報告
- Place of Presentation
  東京工業大学
- Year and Date
  2012-12-21
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 自動発音評定における母音置換規則の検討2012
- Author(s)
  佐藤慶, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学
- Year and Date
  2012-03-09
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 教師なし音響・言語モデル適応の性能改善2011
- Author(s)
  宮本太郎,加藤正治,小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  早稲田大学
- Year and Date
  2011-03-10
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 日本人英語の自動発音評定における精度向上の検討2011
- Author(s)
  久住大,加藤正治,小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  早稲田大学
- Year and Date
  2011-03-10
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 少量のデータによるヒストグラム同等化法の検討2011
- Author(s)
  湊竜一, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  島根大学
- Year and Date
  2011-09-20
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 少量のデータによるヒストグラム同等化法の検討2011
- Author(s)
  湊竜一,加藤正治,小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  島根大学松江キャンパス
- Year and Date
  2011-09-20
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 日本人英語と米国人英語の音素モデル間距離の検討2010
- Author(s)
  久住大,加藤正治,小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  関西大学千里山キャンパス
- Year and Date
  2010-09-16
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] Quinphone HM-Netに基づく講演音声認識2010
- Author(s)
  加藤正治, 小坂哲夫, 伊藤彰則, 牧野正三
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  関西大学
- Year and Date
  2010-09-14
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] Quinphone HM-netを用いた単語グラフ統合に基づく講演音声認識2010
- Author(s)
  加藤正治,小坂哲夫,伊藤彰則,牧野正三
- Organizer
  電子情報通信学会技術研究報告
- Place of Presentation
  九州大学筑紫キャンパス
- Year and Date
  2010-06-18
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] Quinphone HM-Netに基づく講演音声認識2010
- Author(s)
  加藤正治,小坂哲夫,伊藤彰則,牧野正三
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  関西大学千里山キャンパス
- Year and Date
  2010-09-14
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 単語グラフ統合を用いた種々の雑音環境下での音声認識2010
- Author(s)
  倉又俊輔,加藤正治,小坂哲夫
- Organizer
  電子情報通信学会技術研究報告
- Place of Presentation
  仙台市秋保温泉
- Year and Date
  2010-07-23
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 日本人英語と米国人英語の音素モデル間距離の検討2010
- Author(s)
  久住大, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会講演論文集
- Place of Presentation
  関西大学
- Year and Date
  2010-09-16
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] Effectiveness of speaker-class models for the corpus of spontaneous Japanese2008
- Author(s)
  Y. Takeda, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  ASJ 2008 Spring Meeting, 1-Q-21
- Place of Presentation
  Chiba Institute of Technology
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Lecture speech recognition by iterations of unsupervised adaptation2007
- Author(s)
  T. Kusama, Y. Okuyama, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  ASJ 2007 Autumn Meeting, 2-3-14
- Place of Presentation
  University of Yamanashi
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Improvement of unsupervised adaptation in lecture speech recognition2007
- Author(s)
  T. Kusama, Y. Okuyama, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  IEICE Technical Report SP2007-20
- Place of Presentation
  University of Aizu
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] An investigation on speaker vector-based speaker identification under noisy conditions2007
- Author(s)
  Y. Goto, T. Akatsu, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  IEICE Technical Report SP2007-18
- Place of Presentation
  University of Aizu
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] An effect of reduction of dimension on the speaker identification using a speaker vector2007
- Author(s)
  T. Akatsu, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  ASJ 2007 Spring Meeting, 1-P-18
- Place of Presentation
  Shibaura Institute of Technology
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Spontaneous speech recognition using discrete-mixture HMMs2007
- Author(s)
  T. Kosaka, M. Katoh, M. Kohda
- Organizer
  The 19th International Congress on Acoustics
- Place of Presentation
  Madrid, Spain
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Spontaneous speech recognition using discrete-mixture HMMs2007
- Author(s)
  T., Kosaka
- Organizer
  International Congress on Acoustics 2007
- Place of Presentation
  マドリード、スペイン
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] An investigation on the speaker vector-based speaker identification method with phonetic-class HMMs2007
- Author(s)
  T. Akatsu, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  IEICE Technical Report SP2007-135
- Place of Presentation
  NTT CS Laboratories
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Lecture speech recognition by using codebook adaptation of discrete-mixture HMMs2006
- Author(s)
  A. Yamamoto, T. Kumakura, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  IPSJ SIG Technical Report 2006-SLP-62
- Place of Presentation
  Naruto Spa
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Language model adaptation for conference speech transcription2006
- Author(s)
  M. Katoh, T. Kosaka, M. Kohda
- Organizer
  ASJ 2006 Autumn Meeting, 2-P-29
- Place of Presentation
  Kanazawa University
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] An investigation on the acoustic model of the speaker identification using a speaker vector2006
- Author(s)
  T. Akatsu, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  ASJ 2006 Autumn Meeting, 2-P-10
- Place of Presentation
  Kanazawa University
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Codebook normalization of discrete-mixture HMMs by using histogram equalization2006
- Author(s)
  T. Kosaka, M. Katoh, M. Kohda
- Organizer
  MICE Technical Report SP2006-15
- Place of Presentation
  Tohoku University
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] An investigation on the speaker vector-based speaker identification with phonetic modeling2006
- Author(s)
  T. Akatsu, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  IEICE Technical Report SP2006-101
- Place of Presentation
  Nagoya University
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Noisy speech recognition based on codebook normalization of discrete-mixture HMMs2006
- Author(s)
  T., Kosaka
- Organizer
  ASA/ASJ 4th Joint Meeting
- Place of Presentation
  ハワイ、米国
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Noisy speech recognition based on codebook normalization of discrete-mixture HMMs2006
- Author(s)
  T. Kosaka, M. Katoh, M. Kohda
- Organizer
  ASA/ASJ 4th Joint Meeting
- Place of Presentation
  Hawaii, USA
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] 離散混合分布HMMのヒストグラム同等化を用いたコードブック正規化2006
- Author(s)
  小坂哲夫
- Organizer
  電子情報通信学会技術研究報告、SP2006-15
- Place of Presentation
  東北大学
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] Lecture speech recognition by using codebook adaptation of discrete-mixture HMMs2006
- Author(s)
  A. Yamamoto, T. Kumakura, M. Katoh, T. Kosaka, M. Kohda
- Organizer
  ASJ 2006 Autumn Meeting, 2-2-9
- Place of Presentation
  Kanazawa University
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-18500126
[Presentation] クロスバリデーションによる教師なし言語適応における各種パラメータの最適化
- Author(s)
  高木瑛, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 入力音声の韻律情報を用いたHMM音声合成
- Author(s)
  栗原大樹, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Data Source
  KAKENHI-PROJECT-22500144
[Presentation] 最尤推定による話者クラスDNNの出力統合を用いた音声認識
- Author(s)
  今野和樹，加藤正治，小坂哲夫
- Organizer
  日本音響学会春季講演論文集
- Place of Presentation
  中央大学後楽園キャンパス
- Year and Date
  2015-03-16 – 2015-03-18
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] DNN-HMMを用いた教師なしクロス適応の性能改善の検討
- Author(s)
  高木瑛, 加藤正治, 小坂哲夫
- Organizer
  日本音響学会春季講演論文集
- Place of Presentation
  中央大学後楽園キャンパス
- Year and Date
  2015-03-16 – 2015-03-18
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] Deep Learningによる教師つき適応の結果を用いた日本語講演音声認識の誤り解析
- Author(s)
  小野瑞穂，小関翔太，加藤正治，小坂哲夫
- Organizer
  日本音響学会秋季講演論文集
- Place of Presentation
  北海学園大学豊平キャンパス
- Year and Date
  2014-09-03 – 2014-09-05
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] 雑音重複区間のモデル化による音声区間検出の性能向上
- Author(s)
  佐々木志貢, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会東北支部研究会
- Place of Presentation
  山形大学工学部
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] DNN-HMMを用いた音響モデルおよび言語モデルのクロス適応
- Author(s)
  高木瑛, 今野和樹, 加藤正治, 小坂哲夫
- Organizer
  情報処理学会声言語情報処理研究報告
- Place of Presentation
  東京工業大学　大岡山キャンパス
- Year and Date
  2014-05-22 – 2014-05-23
- Data Source
  KAKENHI-PROJECT-25330183
[Presentation] 音声認識におけるDNNを用いた話者クラスモデルの検討
- Author(s)
  今野和樹，高木　瑛，加藤正治，小坂哲夫
- Organizer
  電気関係学会東北支部連合大会
- Place of Presentation
  山形大学工学部
- Year and Date
  2014-08-21 – 2014-08-22
- Data Source
  KAKENHI-PROJECT-25330183

1. KATO Masaharu (10250953)

# of Collaborated Projects: 6 results

# of Collaborated Products: 125 results
2. KOHDA Masaki (00205337)

# of Collaborated Projects: 3 results

# of Collaborated Products: 50 results
3. 井上雅史

# of Collaborated Projects: 0 results

# of Collaborated Products: 1 results

Kosaka Tetsuo 小坂 哲夫

KOSAKA Tetsuo 小坂 哲夫

Research Projects

Research Products

Co-Researchers

Development of emotion recognition system by transfer learning for various speechesPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Emotion detection from speech using high-accuracy emotional speech recognitionPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

A study on acoustic model adaptation for deep-learning-based speech recognitionPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Automatic classification of speech and audio signals using large-scale corpus and its application to speech recognitionPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Development of high-accuracy system for recognizing spontaneous speechPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Large-vocabulary continuous speech recognition on spontaneous speech task

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Development of Noise Robust Speech Recognition and Its Application on Mobile EnvironmentPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Spontaneous speech recognition

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

[Book] 進化するヒトと機械の音声コミュニケーション第1編2章2015

Author(s)

Total Pages

Publisher

Data Source

[Book] "Improvement of Lecture Speech Recognition by Using Unsupervised Adaptation," E-Activity and IntelligentWeb Construction: Effects of Social Design2011

Author(s)

Publisher

Data Source

[Book] 電子情報通信学会知識ベース ,2群画像・音・言語,7編音声認識と合成 ,「2-4話者・環境適応」(原島博, 他編)2011

Author(s)

Total Pages

Publisher

Data Source

[Book] Robust Speech Recognition and Understanding2007

Author(s)

Publisher

Description

Data Source

[Book] Robust Speech Recognition and Understanding2007

Author(s)

Total Pages

Publisher

Data Source

[Journal Article] Simultaneous Adaptation of Acoustic and Language Models for Emotional Speech Recognition Using Tweet Data2024

Author(s)

Journal Title

Kosaka Tetsuo 小坂哲夫

KOSAKA Tetsuo 小坂哲夫