Integrated research on augmentation and assisting technologies forauditory and speech functions

2010 Fiscal Year Final Research Report

• Project/Area Number: 19200017
• Research Category: Grant-in-Aid for Scientific Research (A)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Wakayama University
• Principal Investigator: KAWAHARA Hideki Wakayama University, システム工学部, 教授 (40294300)
• Co-Investigator(Kenkyū-buntansha): IRINO Toshio 和歌山大学, システム工学部, 教授 (20346331) ; NISIMURA Ryuichi 和歌山大学, システム工学部, 助教 (00379611) ; OKUNO Hiroshi 京都大学, 情報学研究科, 教授 (60318201) ; SHIKANO Kiyohiro 奈良先端科学技術大学院大学, 情報科学研究科, 教授 (00263426) ; SARUWATARI Hiroshi 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (30324974) ; SARUWATARI Hiroshi 奈良先端科学技術大学院大学, 情報科学研究科, 准教授 (90403328) ; MORISE Masahiro 立命館大学, 情報理工学部, 助教 (60510013)
• Co-Investigator(Renkei-kenkyūsha): TAKAHASHI Tohru 京都大学, 情報学研究科, 助教 (30419494)
• Research Collaborator: BANNO Hideki 名城大学, 理工学部, 准教授 (20335003) ; PATTERSON Roy 英国Cambridge大学, CNBH, 上級研究員 ; KEWLEY-PORT Diane 米国インディアナ大学, 音声聴覚学科, 名誉教授 ; SCHWEINBERGER Stefan R 独イェナ大学, 心理学部, 教授 ; BELIN Pascal 英国グラスゴー大学, 心理学科, 教授 ; VATIKIOTIS-BATESON Eric カナダブリティッシュコロンビア大学, 言語学科, 教授
• Project Period (FY): 2007 – 2010
• Keywords: 聴覚障害 / 喉頭摘出 / 音声分析 / 音声変換 / 音声合成 / 音源分離 / 聴覚モデル

Research Abstract

Assisting technologies for hearing impaired and esophageal speech and augmentation technologies for voice conversion and manipulation were introduced as the accomplishment of this project, which are constructed by integrating our advanced speech analysis, modification and synthesis framework, computational model of auditory periphery, statistical voice conversion method, and independent constituent technologies were also advanced further and resulted in establishment of strong basis for speech communication research and applications.

Research Products

• [Journal Article] スペクトルピークを強調したF0適応型スペクトル包絡抽出法の最適化と評価 (2011)
  • Author(s): 赤桐隼人, 森勢将雅, 入野俊夫, 河原英紀
  • Journal Title: 電子情報通信学会論文誌 A,Vol.J94-A, No.8
  • Peer Reviewed
• [Journal Article] Esophageal speech enhancement based on statistical voice conversion with Gaussian mixture models (2010)
  • Author(s): H.Doi, K.Nakamura, T.Toda, H.Saruwatari, K.Shikano
  • Journal Title: IEICE Transactions on Information and Systems Vol.E93-D, No.9 Pages: 2472-2482
  • Peer Reviewed
• [Journal Article] 検出に基づく高SNRの音声を対象とした高速なFO推定法 (2010)
  • Author(s): 森勢将雅、河原英紀、西浦敬信、基本波
  • Journal Title: 電子情報通信学会論文誌D Vol.J93-D, No.2 Pages: 109-117
  • Peer Reviewed
• [Journal Article] 分析時刻に依存しない周期信号のパワースペクトル推定法を用いた音声分析 (2010)
  • Author(s): 森勢将雅、高橋徹、入野俊夫、河原英紀
  • Journal Title: 電子情報通信学会 Vol.J92-A, No.3 Pages: 163-171
  • Peer Reviewed
• [Journal Article] 音声モーフィングの背景と可能性 (2009)
  • Author(s): 河原英紀
  • Journal Title: 音声言語医学 Vol.50, No.2 Pages: 185-190
• [Presentation] ICAによる雑音推定に基づいた平均二乗誤差最小化短時間振幅スペクトル推定法の両耳補聴器への応用 (2011)
  • Author(s): 呉将延, 猿渡洋, 鹿野清宏, 細井裕司
  • Organizer: 日本音響学会2011年春季研究発表会
  • Place of Presentation: 早稲田大学
  • Year and Date: 2011-03-10
• [Presentation] 統計的声質変換に基づく無喉頭音声強調法の評価 (2011)
  • Author(s): 土井啓成, 中村圭吾, 戸田智基, 猿渡洋, 鹿野清宏
  • Organizer: 2011年春季研究発表会
  • Place of Presentation: 日本音響学会早稲田大学
  • Year and Date: 2011-03-09
• [Presentation] Evaluation of voice morphing using vocal tract length normalization based on auditory filterbank (2011)
  • Author(s): E.Okamoto, T.Irino, H. Kawahara
  • Organizer: NCSP'11
  • Place of Presentation: Tianjin SaiXiang Hotel, Tianjin, China
  • Year and Date: 2011-03-02
• [Presentation] 成分位相の制御により声の肌触りを変える (2011)
  • Author(s): 河原英紀、ロイ・パターソン、森勢将雅、坂野秀樹、津崎実、高橋徹、西村竜一、入野俊夫
  • Organizer: インタラクション2011
  • Place of Presentation: 日本科学未来館
  • Year and Date: 2011-03-01
• [Presentation] 周期信号における時間的変動の影響を受けない位相関連情報の表現について (2010)
  • Author(s): 河原英紀、森勢将雅、入野俊夫
  • Organizer: 電子情報通信学会技術研究報告SP、音声,Vol.110, No.297,47-51
  • Place of Presentation: 愛知県立大
  • Year and Date: 2010-11-18
• [Presentation] Effects of modelling withinand between-frame temporal variations in power spectra on non-verbal sound recognition (2010)
  • Author(s): N.Yamakawa, T.Kitahara, 高橋徹, K.Komatani, T.Ogata, H.G. Okuno
  • Organizer: Interspeech2010
  • Place of Presentation: Makuhari Messe, Chiba, Japan
  • Year and Date: 2010-09-29
• [Presentation] Exploration of the other aspect of Vocoder revisited (2010)
  • Author(s): 河原英紀
  • Organizer: A-Z STRAIGHT, TANDEM-STRAIGHT and morphing, SSW7
  • Place of Presentation: Kyoto, Japan
  • Year and Date: 2010-09-23
• [Presentation] Banno, High-quality and light-weight voice transformation enabling extrapolation without perceptual and objective breakdown (2010)
  • Author(s): 河原英紀, 西村竜一, 入野俊夫, M.Morise, 高橋徹, H.
  • Organizer: ICASSP2010
  • Place of Presentation: Dallas Texas, USA,
  • Year and Date: 2010-03-18
• [Presentation] Statistical approach to enhancing esophageal speech based on Gaussian mixture models (2010)
  • Author(s): H.Doi, K.Nakamura, T.Toda, H.Saruwatari, K.Shikano
  • Organizer: ICASSP2010
  • Place of Presentation: Dallas Texas, USA
  • Year and Date: 2010-03-18
• [Presentation] MMSE STSA Estimator with nonstationary noise estimation based on ICA for high-quality speech enhancement (2010)
  • Author(s): R.Okamoto, Y.Takahashi, H.Saruwatari, K.Shikano
  • Organizer: ICASSP2010
  • Place of Presentation: Dallas Texas, USA
  • Year and Date: 2010-03-17
• [Presentation] Missing-featuretheory-based robust simultaneous speech recognition system with non-clean speech acoustic model (2009)
  • Author(s): 高橋徹, K.Nakadai, K.Komatani, T.Ogata, H.G.Okuno
  • Organizer: IROS-2009
  • Place of Presentation: St.Louis, USA
  • Year and Date: 2009-10-13
• [Presentation] Development of exploratory rese arch tools based on TANDEM-STRAIGHT (2009)
  • Author(s): 河原英紀, 高橋徹, M.Morise, H.Bannno
  • Organizer: APSIPA2009
  • Place of Presentation: Sapporo, Japan
  • Year and Date: 2009-10-05
• [Presentation] Electrolaryngeal speech enhancement based on statistical voice conversion (2009)
  • Author(s): K.Nakamura, T.Toda, H.Saruwatari, K.Shikano
  • Organizer: Interspeech2009
  • Place of Presentation: Brighton, UK
  • Year and Date: 2009-09-08
• [Presentation] Temporally variable multi-aspect auditory morphing enabling extrapolation without objective and perceptual breakdown (2009)
  • Author(s): 河原英紀, 西村竜一, 入野俊夫, M.Morise, 高橋徹, H.Banno
  • Organizer: ICASSP2009
  • Place of Presentation: Taipei, Taiwan
  • Year and Date: 2009-04-23
• [Presentation] Design and implementation of 3D auditory scene visualizer towards auditory awareness with face tracking (2008)
  • Author(s): Y.Kubota, K.Komatani, T.Ogata, H.G. Okuno
  • Organizer: ISM08
  • Place of Presentation: Berkeley, CA, USA,
  • Year and Date: 2008-12-16
• [Presentation] Spectral envelope recovery beyond the Nyquist limit for high-quality manipulation of speech sounds (2008)
  • Author(s): 河原英紀, M.Morise, H.Banno, 高橋徹, 西村竜一, 入野俊夫
  • Organizer: Interspeech2008
  • Place of Presentation: Brisbane, Australia
  • Year and Date: 2008-09-24
• [Presentation] Evaluation of speaking-aid system with voice conversion for laryngectomees toward its use in practical environments (2008)
  • Author(s): K.Nakamura, T.Toda, Y.Nakajima, H.Saruwatari, K.Shikano
  • Organizer: Interspeech2008
  • Place of Presentation: Brisbane, Australia
  • Year and Date: 2008-09-24
• [Presentation] TANDEM-STRAIGHT : A temporally stable power spectral representation for periodic signals and applications to interference-free spectrum, FO, and aperiodicity estimation (2008)
  • Author(s): 河原英紀, M.Morise, 高橋徹, 西村竜一, 入野俊夫, H.Banno
  • Organizer: ICASSP2008
  • Place of Presentation: Las Vegas, USA
  • Year and Date: 2008-04-01
• [Book] Consideration Books, Los Angeles,235-243 (2010)
  • Author(s): Hideki Kawahara, Masanori Morise, Toru Takahashi, Ryuichi Nisimura, Hideki Banno, Toshio Irino
  • Total Pages: 644
  • Publisher: STRAIGHT, a framework for speech analysis, modification and synthesis, in Computer processing of Asian spoken languages, (eds. Shuichi Itahashi and Chiu-yu Tseng)
• [Remarks] ホームページ等
  • URL: http://www.wakayama-u.ac.jp/.kawahara/