Analysis of Intra-Speaker Variation and Development of Distributed Speaker Recognition System

• Project/Area Number: 17300065
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Chiba University (2007-2008); The University of Tokushima (2005-2006)
• Principal Investigator: KUROIWA Shingo Chiba University, 大学院・融合科学研究科, 教授 (20333510)
• Co-Investigator(Kenkyū-buntansha): KITA Kenji 徳島大学, 高度情報化基盤センター, 教授 (10243734) ; REN Fuji 徳島大学, 大学院・ソシオテクノサイエンス研究部, 教授 (20264947) ; TSUGE Satoru 徳島大学, 大学院・ソシオテクノサイエンス研究部, 講師 (00325250) ; NISHIDA Masafumi 千葉大学, 大学院・融合科学研究科, 助教 (80361442)
• Co-Investigator(Renkei-kenkyūsha): HORIUCHI Yasuo 千葉大学, 大学院・融合科学研究科, 准教授 (30272347)
• Project Period (FY): 2005 – 2008
• Project Status: Completed (Fiscal Year 2008)
• Budget Amount: ¥16,640,000 (Direct Cost: ¥15,200,000、Indirect Cost: ¥1,440,000); Fiscal Year 2008: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000); Fiscal Year 2007: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000); Fiscal Year 2006: ¥3,300,000 (Direct Cost: ¥3,300,000); Fiscal Year 2005: ¥7,100,000 (Direct Cost: ¥7,100,000)
• Keywords: 音声学 / 話者認識 / 話者識別 / 話者照合 / 音声データベース / 分散型音声認識 / 分散型話者認識 / 分散型話者照合 / 音声変動

Research Abstract

本研究では、音声による個人認証技術である話者認識に関する基礎研究、及び携帯電話での利用を想定した応用研究を行った。基礎研究としては、同一の話者が、毎週1日、朝・昼・夕に2年~4年かけて発声した音声を収集し、時期差・時間差・気分等の様々な要因で個々人の音声がどのように変動するかの解明を試みた。応用研究としては、音声に含まれる個人性の抽出手法、個人音声のモデル化法、モデルと音声の比較手法および判別手法を考案し、従来手法に比べ頑健で高精度な話者認識システムを実現した。

Research Products

• [Journal Article] 書き起こしへの付与を目指した音声とテキストを対象とした発話印象の分析 (2009)
  • Author(s): 西田昌史
  • Journal Title: 情報処理学会論文誌 50 Pages: 460-468
  • NAID: 110007970342
  • Peer Reviewed
• [Journal Article] Distributed Speaker Identification and Verification for Mobile Terminals (2008)
  • Author(s): Shingo Kuroiwa, Satoru Tsuge, Fuji Ren
  • Journal Title: International Journal of Biomedical Soft Computing and Human Sciences Vol.14 Pages: 3-9
  • Peer Reviewed
• [Journal Article] Evaluation of Emotion Estimation Methods Based on Statistic Features of Emotion Tagged Corpus (2008)
  • Author(s): Junko Minato, Kazuyuki Matsumoto, Fuji Ren, Seiji Tsuchiya, Shingo Kuroiwa
  • Journal Title: International Journal of Innovative Computing, Information and Control Vol.4, No.8 Pages: 1931-1941
  • Peer Reviewed
• [Journal Article] Super-Functionに基づく日英機械翻訳における日付・時間表現の抽出 (2008)
  • Author(s): 篠山学
  • Journal Title: 電気学会論文誌C 128 Pages: 1342-1350
  • Peer Reviewed
• [Journal Article] Distributed Speaker Identification and Verification for Mobile Terminals (2008)
  • Author(s): Shingo KUROIWA
  • Journal Title: International Journal of Biomedical Soft Computing and Human Sciences 14 Pages: 3-9
  • Peer Reviewed
• [Journal Article] Speaker Identification Method Using Earth Mover's Distance for CCC Speaker Recognition Evaluation 2006 (2007)
  • Author(s): Shingo Kuroiwa, Satoru Tsuge, Masahiko Kita, Fuji Ren
  • Journal Title: International Journal of Computational Linguistics & Chinese Language Processing Vol.12 Pages: 239-254
  • Peer Reviewed
• [Journal Article] 感情生起事象文型パターンに基づいた会話文からの感情推定手法 (2007)
  • Author(s): 松本和幸, 三品賢一, 任福継, 黒岩眞吾
  • Journal Title: 自然言語処理 Vol.14
  • NAID: 10020153615
  • Peer Reviewed
• [Journal Article] "分散音声認識における実時間周波数特性正規化手法 (2007)
  • Author(s): 柘植覚, 黒岩眞吾, 獅々堀正幹, 任福継, 北研二
  • Journal Title: 情報処理学会論文誌 Vol.48 Pages: 900-908
  • NAID: 110006207810
  • Peer Reviewed
• [Journal Article] 感情生起事象文型パターンに基づいた会話文からの感情推定手法 (2007)
  • Author(s): 松本 和幸
  • Journal Title: 自然言語処理 14 Pages: 239-271
  • Peer Reviewed
• [Journal Article] Chinese Semantic Dependeney Analysis: Construction of a Treebank and its Use in Classification (2007)
  • Author(s): Hua Xiang
  • Journal Title: ACM Transactions on Speech and Language Processing 4 Pages: 722-731
  • Peer Reviewed
• [Journal Article] 符号化音声認識のための合成音声を用いた不特定話者音響モデルの趨応法 (2007)
  • Author(s): 原一 眞
  • Journal Title: 電子情報通信学会論文誌(D) J90-D Pages: 2541-2549
  • Peer Reviewed
• [Journal Article] Speaker Identification Method Using Earth Mover,s Distance for CCC Speaker Recognition Evaluation 2006 (2007)
  • Author(s): Shingo Kuroiwa
  • Journal Title: International Journal of Computational Linguistics & Chinese Language Processing 12 Pages: 239-254
  • Peer Reviewed
• [Journal Article] Sentence alignment using P-NNT and GMM (2007)
  • Author(s): Mohamed Abdel Fattah
  • Journal Title: Computer Speech and Language 21 Pages: 594-608
  • Peer Reviewed
• [Journal Article] スペクトルの微細構造を考慮した風雑音除去手法 (2007)
  • Author(s): 黒岩 眞吾
  • Journal Title: 電子情報通信学会論文誌(A) J90-A・1 Pages: 1-12
  • NAID: 10018038368
• [Journal Article] 分散音声認識における実時間周波数特性正規化手法 (2007)
  • Author(s): 柘植 覚
  • Journal Title: 情報処理学会論文誌 48・2 Pages: 900-908
  • NAID: 110006207810
• [Journal Article] A Model of Mental state Transition Network (2007)
  • Author(s): Hua Xiang
  • Journal Title: IEEJ Transactions on Electronics, Information and Systems 127-C・3 Pages: 434-442
• [Journal Article] Effects of Phoneme Type and Frequency on Distributed Speaker Identification and Verification (2006)
  • Author(s): Mohamed Abdel Fattah, Fuji Ren, Shingo Kuroiwa
  • Journal Title: IEICE Transactions on Information and Systems Vol.E89-D Pages: 1712-1719
  • NAID: 110007503083
  • Peer Reviewed
• [Journal Article] Nonparametric Speaker Recognition Method using Earth Mover's Distance (2006)
  • Author(s): Shingo Kuroiwa, Yoshiyuki Umeda, Satoru Tsuge, Fuji Ren
  • Journal Title: IEICE Transactions on Information and Systems Vol.E89-D Pages: 1074-1081
  • NAID: 110004719383
  • Peer Reviewed
• [Journal Article] Specific Speaker's Japanese Speech Corpus over Long and Short Time Periods (2006)
  • Author(s): Satoru Tsuge, Masami Shishibori, Fuji Ren, Kenji Kita, Shingo Kuroiwa
  • Journal Title: Journal of Research on Computing Science Vol.17 Pages: 115-124
  • Peer Reviewed
• [Journal Article] 音声認識・音声合成を用いた音声途切れ補間手法 (2006)
  • Author(s): 黒岩眞吾, 小林邦嘉, 柘植覚, 任福継
  • Journal Title: 日本音響学会誌 Vol.62 Pages: 3-9
  • NAID: 10018035152
  • Peer Reviewed
• [Journal Article] Effects of Phoneme Type and Frequency on Distributed Speaker Identification and Verification (2006)
  • Author(s): Mohamed Abdel Fattah
  • Journal Title: IEICE Transactions on Information and Systems E89・5 Pages: 1712-1719
• [Journal Article] A Mind Model for an Affective Computer (2006)
  • Author(s): Hua Xiang
  • Journal Title: International Journal of Computer Science and Network Security 6・6 Pages: 62-69
• [Journal Article] A New Question Answering System for Chinese Restricted Domain (2006)
  • Author(s): Haiqing Hu
  • Journal Title: IEICE Transactions on Information and Systems E89-D・6 Pages: 1848-1859
• [Journal Article] Non-Verbal Voice Emotion Analysis System (2006)
  • Author(s): Shunji Mitsuyoshi
  • Journal Title: International Journal of Innovative Computing, Information and Control 2・4 Pages: 819-830
• [Journal Article] The Emotion Recognition through classification with the Support Vector Machines (2006)
  • Author(s): Zhi Teng
  • Journal Title: WSEAS Transactions on COMPUTERS 5・9 Pages: 2008-2013
• [Journal Article] The Validity of Metaphor in Emotion Recognizing Model (2006)
  • Author(s): Yu Zhang
  • Journal Title: WSEAS Transactions on COMPUTERS 5・9 Pages: 2049-2055
• [Journal Article] Speaker Recognition for Wire/Wireless Communication Systems (2006)
  • Author(s): Mohamed Abdel Fattah
  • Journal Title: International Arab Journal of Information Technology 3・1 Pages: 28-34
• [Journal Article] 音声認識・音声合成を用いた音声途切れ補間手法 (2006)
  • Author(s): 黒岩 眞吾
  • Journal Title: 音響学会誌 62・1 Pages: 3-9
  • NAID: 10018035152
• [Journal Article] Phoneme Based Speaker Modeling to Improve Speaker Recognition (2006)
  • Author(s): Mohamed Abdel Fattah
  • Journal Title: Information 9・1 Pages: 135-147
• [Journal Article] Acoustic Model Adaptation for Codec Speech based on Learning-by-Doing Concept (2006)
  • Author(s): 黒岩 眞吾
  • Journal Title: Journal of Research on Computing Science 17・1 Pages: 105-114
• [Journal Article] Specific Speaker's Japanese Speech Corpus over Long and Short Time Periods (2006)
  • Author(s): 柘植 覚
  • Journal Title: Journal of Research on Computing Science 17・1 Pages: 115-124
• [Journal Article] Nonparametric Speaker Recognition Method using Earth Mover's Distance (2006)
  • Author(s): 黒岩 眞吾
  • Journal Title: IEICE Transactions on Information and Systems E89-D・3 Pages: 1074-1081
  • NAID: 110004719383
• [Journal Article] Simple PCAを用いたベクトル空間情報検索モデルの次元削減 (2005)
  • Author(s): 黒岩 眞吾
  • Journal Title: 電気学会論文誌C 125・11 Pages: 1773-1779
  • NAID: 130000089848
• [Journal Article] An Advanced Mental State Transtion Network and Psychological experiments (2005)
  • Author(s): Peilin Jiang
  • Journal Title: Lecture Notes in Computer Science 3824・1 Pages: 1026-1035
• [Presentation] 話者認識技術の紹介と最近の研究動向 (2009)
  • Author(s): 黒岩員吾
  • Organizer: 電子情報通信学会・バイオメトリックシステムセキュリティ研究会
  • Place of Presentation: 統計数理研究所(東京)
  • Year and Date: 2009-03-23
• [Presentation] Non-Stationary Noise Robust Speech Recognition Method Using Repetitive Phrase (2009)
  • Author(s): Yasunori Kashihara
  • Organizer: RISP International Workshop on Nonlinear Circuits and Signal Processing
  • Place of Presentation: ホノルル(米国)
  • Year and Date: 2009-03-02
• [Presentation] Evaluation of Fundamental Frequency Prediction from MFCC Using Japanese Utterance (2009)
  • Author(s): Takafumi YUI
  • Organizer: RISP International Workshop on Nonlinear Circuits and Signal Processing
  • Place of Presentation: ホノルル(米国)
  • Year and Date: 2009-03-01
• [Presentation] 音韻変動を抑制する特徴変換に基づく話者認識 (2009)
  • Author(s): 陸昊澤, 西田昌史, 堀内靖雄, 黒岩眞吾
  • Organizer: 日本音響学会春季研究発表会
  • Place of Presentation: 東京
• [Presentation] 話者認識技術の紹介と最近の研究動向 (2009)
  • Author(s): 黒岩眞吾, 柘植覚
  • Organizer: 電子情報通信学会・バイオメトリックシステムセキュリティ研究会, 第17回研究発表会
  • Place of Presentation: 東京
• [Presentation] 音韻変動を抑制する特徴変換に基づく話者認識 (2009)
  • Author(s): 陸 臭深
  • Organizer: 日本音響学会2009年春季研究発表会
  • Place of Presentation: 東京工業大学(東京)
• [Presentation] Specific Speakers' Speech Corpus Over Long and Short Time Periods, (2008)
  • Author(s): Satoru TSUGE
  • Organizer: Oriental COCOSDA 2008
  • Place of Presentation: けいはんなプラザホテル(京都)
  • Year and Date: 2008-11-25
• [Presentation] Text-Independent Speaker Identification Based on Feature Transformation to Phoneme-Independent Subspace (2008)
  • Author(s): Haoze LU
  • Organizer: IEEE ICCT2008
  • Place of Presentation: 杭州(中国)
  • Year and Date: 2008-11-10
• [Presentation] Combination method of Bone-conduction Speech and Air-conduction Speech for Speaker Recognition (2008)
  • Author(s): Satoru TSUGE
  • Organizer: Interspeech 2008
  • Place of Presentation: ブリスベン(オーストラリア)
  • Year and Date: 2008-09-25
• [Presentation] A Method for Automatically Estimating FO Model Parameters and a Speech Re-Synthesis Tool Using FO Model and STRAIGHT (2008)
  • Author(s): Shota SATO
  • Organizer: Interspeech 2008
  • Place of Presentation: ブリスベン(オーストラリア)
  • Year and Date: 2008-09-23
• [Presentation] 骨導音と気導音を併用した話者識別手法 (2008)
  • Author(s): 柘植 覚
  • Organizer: 日本音響学会春季研究発表会
  • Place of Presentation: 千葉工業大学(津田沼)
  • Year and Date: 2008-03-17
• [Presentation] A Study of Speaker Identification Using Phoneme-lnformation (2008)
  • Author(s): Katsuyuki Obayashi
  • Organizer: 2008 RISP Illternational Workshop on Nonlinear Circuits and Signal Processing
  • Place of Presentation: ゴールドコースト(オーストラリア)
  • Year and Date: 2008-03-06
• [Presentation] Specific Speakers' Speech Corpus Over Long and Short Time Periods (2008)
  • Author(s): Satoru Tsuge, Minoru Fukumi, Shingo Kuroiwa
  • Organizer: Oriental COCOSDA
  • Place of Presentation: Kyoto
• [Presentation] Text-Independent Speaker Identification Based on Feature Transformation to Phoneme-Independent Subspace (2008)
  • Author(s): Haoze Lu, Haruka Okamoto, Masafumi Nishida, Yasuo Horiuchi, Shingo Kuroiwa
  • Organizer: 11th IEEE International Conference on Communication Technologies
  • Place of Presentation: Hangzhou, China
• [Presentation] Combination method of Bone-conduction Speech and Air-conduction Speech for Speaker Recognition (2008)
  • Author(s): Satoru Tsuge, Osanai Takashi, Makinae Hisanori, Kamada Toshiaki, Minoru Fukumi, Shingo Kuroiwa
  • Organizer: Interspeech
  • Place of Presentation: Brisbane, Australia
• [Presentation] 大規模話者骨導音声データベースを用いたテキスト独立型話者照合実験 (2007)
  • Author(s): 喜多 雅彦
  • Organizer: 音声言語ワークショップ
  • Place of Presentation: NTT京阪奈ビル(けいはんな学研都市)
  • Year and Date: 2007-12-20
• [Presentation] 日本語大規模話者認識用データベースを用いた話者識別実験 (2007)
  • Author(s): 柘植 覚
  • Organizer: 日本音響学会秋季研究発表会,
  • Place of Presentation: 山梨大学(甲府)
  • Year and Date: 2007-09-21
• [Presentation] Emotion Recognition from Text based on the Rough Set Theory and the Support Vector Machines (2007)
  • Author(s): Zhi TENG
  • Organizer: IEEE NLP-KE2007
  • Place of Presentation: 北京(中国)
  • Year and Date: 2007-09-01
• [Presentation] An Emotion Similarity Calculation Using N-gram Frequency (2007)
  • Author(s): Mishina Kenichi
  • Organizer: IEEE NLP-KE2007
  • Place of Presentation: 北京(中国)
  • Year and Date: 2007-09-01
• [Presentation] A speech emphasis method for noise-robust speech recognition by usingrepetitive phrase (2007)
  • Author(s): Takanori Hirpai
  • Organizer: IEEE NLP-KE2007
  • Place of Presentation: 北京(中国)
  • Year and Date: 2007-09-01
• [Presentation] Corpus Based Analysis of Japanese-English Einotional Expressions (2007)
  • Author(s): Junko Minato
  • Organizer: IEEE NLP-KE2007
  • Place of Presentation: 北京(中国)
  • Year and Date: 2007-08-31
• [Presentation] Analysis of Variatio of Intra-Speakers Speech Recognition Perforinances (2007)
  • Author(s): Satoru Tsuge
  • Organizer: IEEE NIP-KE2007
  • Place of Presentation: 北京(中国)
  • Year and Date: 2007-08-31
• [Presentation] Automatic Utterance Segmentation Tool for Speech Corpus (2007)
  • Author(s): Mitsuhiro Ozawa
  • Organizer: IEEE NLP-KE2007
  • Place of Presentation: 北京(中国)
  • Year and Date: 2007-08-31
• [Presentation] Artificial Bandwidth Extension for Speech Signals using Speech Recogllition (2007)
  • Author(s): Shingo Kuroiwa
  • Organizer: Interspeech2007,
  • Place of Presentation: アントワープ(ベルギー)
  • Year and Date: 2007-08-31
• [Presentation] 感情コーパス構築のための文中の語に基づく感情分類手法 (2007)
  • Author(s): 山本 麻由
  • Organizer: 情報処理学会研究報告「自然言語処理」
  • Place of Presentation: 徳島大学(徳島)
  • Year and Date: 2007-07-24
• [Presentation] N-gram出現頻度を用いた感情類似度計算 (2007)
  • Author(s): 三品 賢一
  • Organizer: 情報処理学会研究報告「自然言語処理」
  • Place of Presentation: 徳島大学(徳島)
  • Year and Date: 2007-07-24
• [Presentation] 突発性雑音に頑健な音声認識実現のための繰り返し発声を用いた音声強調法の提案 (2007)
  • Author(s): 平井 孝則
  • Organizer: 人工知能学会言語・音声理解と対話処理研究会
  • Place of Presentation: 徳島大学(徳島)
  • Year and Date: 2007-07-23
• [Presentation] 多数の話者モデル内での順位情報を用いた話者照合 (2007)
  • Author(s): 喜多 雅彦
  • Organizer: 人工知能学会 言語・音声理解と対話処理研究会
  • Place of Presentation: 徳島大学(徳島)
  • Year and Date: 2007-07-23
• [Presentation] 分散音声認識を用いた音声対話システムの検討 (2007)
  • Author(s): 藤原 祥平
  • Organizer: 人工知能学会言語・音声理解と対話処理研究会
  • Place of Presentation: 徳島大学(徳島)
  • Year and Date: 2007-07-23
• [Presentation] SeIni-Automatic Construction of an Emotion Ontology Ushlg HowNet (2007)
  • Author(s): Jiajun Yan
  • Organizer: the 2007 Intematiomal Conference on Artificial Intelligence and Pattem Recognition
  • Place of Presentation: フロリダ(米国)
  • Year and Date: 2007-07-09
• [Presentation] 大規模話者骨導音声データベースを用いたテキスト独立型話者照合実験 (2007)
  • Author(s): 喜多雅彦, 黒岩眞吾, 柘植覚, 蒔苗久則, 長内隆, 鎌田敏明, 谷本益巳, 土屋誠司, 福見稔, 任福継
  • Organizer: 第9回音声言語シンポジウム
  • Place of Presentation: 京都
• [Presentation] Analysis of Variation on Intra-Speakers Speech Recognition Performances (2007)
  • Author(s): Satoru Tsuge, Keiji SEIDA, Masami Shishibori, Kenji Kita, Fuji Ren, Minoru Fukumi Shingo Kuroiwa
  • Organizer: IEEE NLP-KE2007
  • Place of Presentation: Beijing, China
• [Presentation] 多数の話者モデル内での順位情報を用いた話者照合 (2007)
  • Author(s): 喜多雅彦, 柘植覚, 黒岩眞吾, 任福継
  • Organizer: 人工知能学会言語・音声理解と対話処理研究会, SIG-SLUD-A701-2
  • Place of Presentation: 徳島
• [Presentation] Study of Relationships Between Intra-Speaker's Speech Variability and Speech Recognition Performance (2006)
  • Author(s): Satoru Tsuge, Minoru Fukumi, Masami Shishibori, Fuji Ren, Kenji Kit, Shingo Kuroiwa
  • Organizer: 2006 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2006)
  • Place of Presentation: Tottori
• [Presentation] Evaluation of EMD-based Speaker Recognition using ISCSLP2006 Chinese Speaker Recognition Evaluation Corpus (2006)
  • Author(s): Shingo Kuroiwa, Satoru Tsuge, Masahiko Kita and Fuji Ren
  • Organizer: 5th International Symposium on Chinese Spoken Language Processing
  • Place of Presentation: Kent Ridge, Singapore
• [Presentation] Study of Intra-Speaker's Speech Variability over Long and Short Time Periods for Speech Recognition (2006)
  • Author(s): Satoru Tsuge, Masami Shishibori, Kenji Kita, Fuji Ren, Shingo Kuroiwa
  • Organizer: IEEE International Conference on Acoustic, Speech, and Signal Processing
  • Place of Presentation: Toulouse, France
• [Presentation] Data Collection for Investigating Speech Variability in a Specific Speaker Over Long and Short Time Periods (2005)
  • Author(s): Satoru Tsuge, Masami ShiShibori, Kenji Kita, Shingo Kuroiwa
  • Organizer: IEEE International Conference on Natural Language Processing and Knowledge Engineering
  • Place of Presentation: Wuhan, China
• [Presentation] Distributed Speaker Recognition using Speaker- Dependent VQ Codebook and Earth Mover's Distance (2005)
  • Author(s): Shingo Kuroiwa, Yoshiyuki Umeda, Satoru Tsuge, Fuji Ren
  • Organizer: INTERSPEECH 2005
  • Place of Presentation: Lisbon