A study of robust speech recognition method for intra-speakers' speech variability

2009 Fiscal Year Self-evaluation Report

• Project/Area Number: 19700172
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Single-year Grants
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: The University of Tokushima
• Principal Investigator: SATORU Tsuge The University of Tokushima, 大学院・ソシオテクノサイエンス研究部, 講師 (00325250)
• Project Period (FY): 2007 – 2010
• Keywords: 音声認識 / 特定話者 / 話者内音声変動

Research Abstract

本研究は、同一発声者が特定の音声認識(話者依存音声認識)システムを使用した場合においても必ず毎回同一の音声認識結果とならないという問題を取り扱うものである。この個々人が同一内容を発声したとしても、気分や発声環境により変動(音声変動)する原因を解明し、音声認識精度の変動を抑制することが本研究の目的である。

Research Products

• [Presentation] Non-Stationary Noise Robust Speech Recognition Method using Repetitive Phrase (2009)
  • Author(s): Yasunori Kashihara, Satoru Tsuge, Kipsang H. Choge, Tadahiro Oyama, Minoru Fukumi, Shingo Kuroiwa
  • Organizer: Proc. of NCSP'2009
  • Place of Presentation: Hawaii U.S. A
  • Year and Date: 20090000
• [Presentation] 繰り返し発声を用いた突発性雑音に頑健な音声認識に関する研究 (2009)
  • Author(s): 柏原康徳, 柘植覚, 尾山匡浩, Choge Hillary Kipsang, 福見稔, 黒岩眞吾
  • Organizer: 平成21年度電気学会電子情報システム部門大会
  • Place of Presentation: 徳島
  • Year and Date: 20090000
• [Presentation] 気導音と骨導音を併用した話者ベクトルを用いた話者識別 (2009)
  • Author(s): 中尾昌史, 柘植覚, 福見稔
  • Organizer: 平成21年度電気学会電子情報システム部門大会
  • Place of Presentation: 徳島
  • Year and Date: 20090000
• [Presentation] Speaker verification method using boneconduction and air- conduction speech (2009)
  • Author(s): Satoru Tsuge, Daichi Koizumi, Minoru Fukumi, Shingo Kuroiwa
  • Organizer: Proc. of ISPACS 2009
  • Place of Presentation: Kanazawa Japan
  • Year and Date: 20090000
• [Presentation] Text-Independent Speaker Verification Using Rank Threshold in Large Number of Speaker Models (2009)
  • Author(s): Haruka Okamoto, Amira Abdelwahab, Masahumi Nishida, Satoru Tsuge, Yasuo Horiuchi, Shingo Kuroiwa
  • Organizer: Proc. of InterSpeech 2009
  • Place of Presentation: Brighton U.K.
  • Year and Date: 20090000
• [Presentation] A Study of speaker identification using phoneme-information (2008)
  • Author(s): Katsuyuki Oobayashi, Satoru Tsuge, Minoru Fukumi, Seiji Tsuchiya, Ryosuke Sumitomo, Fuji Ren, Shingo Kuroiwa
  • Organizer: Proc. of NCSP'2008
  • Place of Presentation: Gold Coast, Australia
  • Year and Date: 20080300
• [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, 喜多雅彦, 長内隆, 蒔苗久 則, 鎌田敏明, 谷本益巳, 福見稔, 任福継、黒岩眞吾
  • Organizer: 日本音響学会秋季研究発表会
  • Place of Presentation: 千葉
  • Year and Date: 20080000
• [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: Proc. of Interspeech 2008
  • Place of Presentation: Brisbane Australia
  • Year and Date: 20080000
• [Presentation] Specific speakers' speech corpus over long and short time period (2008)
  • Author(s): Satoru Tsuge, Minoru Fukumi, Shingo Kuroiwa
  • Organizer: Proc. of oriental COCOSDA
  • Place of Presentation: Kyoto Japan
  • Year and Date: 20080000
• [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: Proc. of IEEE NLP-KE2007
  • Place of Presentation: Beijing China
  • Year and Date: 20071000
• [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, 黒岩 眞吾, 喜多雅彦, 蒔苗久則, 長内隆, 鎌田敏明, 谷本益巳, 福見稔, 任福継
  • Organizer: 日本音響学会春季研究発表会
  • Place of Presentation: 山梨
  • Year and Date: 20070900
• [Presentation] Minoru Fukumi, and Shingo Kuroiwa, Automatic Utterance Segmentation Tool for Speech Corpus (2007)
  • Author(s): Mitsuhiro Ozawa, Satoru Tsuge, Masami Shishibori, Kenji Kita, Fuji Ren, Minoru Fukumi, Shingo Kuroiwa
  • Organizer: Proc. of IEEE NLP-KE2007
  • Place of Presentation: Beijing China
  • Year and Date: 20070000
• [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, 柘植覚, 黒岩眞吾, 任福 継
  • Organizer: 情報処理学会音声言語情報処理
  • Place of Presentation: 京都
  • Year and Date: 20070000