分散して蓄積された音声データを用いて多様な音響モデルを作成するための研究

2004 Fiscal Year Annual Research Report

• Project/Area Number: 15200014
• Research Institution: Nagoya University
• Principal Investigator: 武田 一哉 名古屋大学, 大学院・情報科学研究科, 教授 (20273295)
• Co-Investigator(Kenkyū-buntansha): 鹿野 清宏 奈良先端科学技術大学院大学, 情報科学研究科, 教授 (00263426) ; 河原 達也 京都大学, 学術情報メディアセンター, 教授 (00234104)
• Keywords: 音声認識 / 分散処理 / HMM / モデル補間

Research Abstract

最尤基準により、分散して格納された音声波形(音声パラメータ)を利用して、音響モデルを学習するシステムを作成した.分散学習拠点毎に収録された音声に,共通の処理(音素ラベル付与など)を行い,共通のフォーマットで話者・環境情報を記述するとともに,定めたディレクトリ構造に従って関連ファイルを格納することで,分散データベースを構築する.分散学習拠点には,HMM音響モデルの学習(具体的には,前向き確率の計算を実行し,状態毎の統計量を算出する.)に利用可能な計算サーバも用意した.ユーザは,1)利用を希望する音声データの属性を指定することで,学習に利用可能な音声データのリストを得ることができ,2)学習するHMMの属性(初期モデル)をアップロードすることで,選択したデータを用いてHMMの学習を実行することができる.すなわち,本システムを利用することで,直接音声データを授受することなく分散した音声データを用いて多様な音響モデルの構築を行うことができる.センターは,分散学習拠点でローカルに計算された統計量を統合してHMMパラメータの最尤推定を行い,その結果を保持するとともに,推定されたパラメータを,更新された初期HMMとして分散学習拠点に送り返す.現在までに,名古屋大学,奈良先端大,ASTEMの3つの分散学習拠点が,名古屋大学に設置されたセンターシステムの管理下で動作しており,(車内音声対話、子供の声、公共施設案内対話音声、新聞読み上げ音声、など,延べ17万発話を学習に利用することが可能となった.

Research Products

• [Journal Article] Analysis and Recognition of Whispered Speech (2005)
  • Author(s): Taisuke Ito, Kazuya Takeda, Fumitada Itakura
  • Journal Title: Speech Communication Vol.45 Pages: 139-152
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] AURORA-2J : Japanese speech data collection for performance evaluation of speech recognition in noise (2005)
  • Author(s): Satoshi Nakamura, Kazuya Takeda, Kazumasa Yamamoto, Takeshi Yamada, Shingo Kuroiwa, Norihide Kitaoka, Takanobu Nishiura, Akira Sasou, Mitsunori Mizumachi, Chiyomi
  • Journal Title: IEICE Transactions on Information and Systems (in print)
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 長時間の音声対話インタフェース利用時における学習効果の評価 (2005)
  • Author(s): 原直, 白勢彩子, 宮島千代美, 伊藤克亘, 武田一哉
  • Journal Title: 日本音響学会講演論文集 2-Q-28 Pages: 153-154
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 頭部伝達関数を用いた自由聴点立体音場の構築と評価 (2005)
  • Author(s): 水野渉, 木村敏幸, 西野隆典, 武田一哉
  • Journal Title: 日本音響学会講演論文集 3-Q-29 Pages: 563-564
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] バイモーダル車内音声認識評価用データベースの構築 (2005)
  • Author(s): 根木大輔, 前野俊希, 北坂孝幸, 森健策, 末永康仁, 宮島千代美, 伊藤克亘, 武田一哉, 板倉文忠, 佐野昌己, 二宮芳樹
  • Journal Title: 情報処理学会研究報告 2005-SLP-55(7) Pages: 35-40
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 実走行車内単語音声データベースCENSREC-3と共通評価環境の構築 (2005)
  • Author(s): 藤本雅清, 中村哲, 武田一哉, 黒岩眞吾, 山田武志, 北岡教英, 山本一公, 水町光徳, 西浦敬信, 佐宗晃, 宮島千代美, 遠藤俊樹
  • Journal Title: 情報処理学会研究報告 2005-SLP-55(8) Pages: 41-46
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Language model adaptation based on PLSA of topics and speakers for automatic transcription of panel discussions (2005)
  • Author(s): Y.Akita, T.Kawahara
  • Journal Title: IEICE Trans. Vol.E88-D, No.3 Pages: 239-445
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Dialogue speech recognition by combining hierarchical topic classification and language model switching (2005)
  • Author(s): I.R.Lane, T.Kawahara, T.Matsui, S.Nakamura
  • Journal Title: IEICE Trans. Vol.E88-D, No.3 Pages: 446-454
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] The Present Status, Progress, and Usage of Speech Databases in Japan (Technical Report) (2005)
  • Author(s): Hisao Kuwabara, Shuichi Itahashi, Mikio Yamamoto, Saotshi Nakamura, Toshiyuki Takezawa, Kazuya Takeda
  • Journal Title: Acoustic Science and Technologies Vol.26, No.1 Pages: 62-66
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Construction and Evaluation of a Large in-car Speech Corpus (2005)
  • Author(s): Kazuya Takeda, Hiroshi Fujimura, Katsunobu Itou, Nobuo Kawaguchi, Shigeki Matsubara, Fumitada Itakura
  • Journal Title: IEICE Transactions on Information and Systems Vol.EE88-D, No.3 Pages: 553-561
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Designing target cost function based on prosody of speech database (2005)
  • Author(s): Kazuki Adachi, Tomoki Toda, Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: IEICE Trans.Inf. and Syst. (accepted)
• [Journal Article] Multistage SIMO-based blind source separation combining frequency-domain ICA and time-domain ICA (2005)
  • Author(s): Satoshi Ukai, Tomoya Takatani, Hiroshi Saruwatari, Kiyohiro Shikano, Ryo Mukai, Hiroshi Sawada
  • Journal Title: IEICE Trans.Fundamentals Vol.E88-A, No.3(in printing)
• [Journal Article] Interface for barge-in free spoken dialogue system combining adaptive sound field control and microphone array (2005)
  • Author(s): Tatsunori Asai, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: IEICE Trans.Fundamentals (accepted)
• [Journal Article] Blind source separation based on fast-convergence algorithm combining ICA and beamforming (2005)
  • Author(s): Hiroshi Saruwatari, Toshiya Kawamura, Tsuyoki Nishikawa, Akinobu Lee, Kiyohiro Shikano
  • Journal Title: IEEE Transactions on Speech and Audio Processing (accepted)
• [Journal Article] Blind Source Separation Combining SIMO-Model-Based ICA and Adaptive Beamforming (2005)
  • Author(s): Satoshi Ukai, Tomoya Takatani, Tsuyoki Nishikawa, Hiroshi Saruwatari
  • Journal Title: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2005) (in printing)
• [Journal Article] Two-Stage Blind Source Separation Using SIMO-ICA and Binary Masking (2005)
  • Author(s): Hiroshi Saruwatari, Yoshimitsu Mori, Tomoya Takatani, Satoshi Ukai, Kiyohiro Shikano, Takashi Hiekata, Takashi Morita
  • Journal Title: Proceedings of Joint Workshop on Hands-Free Speech Communication and Microphone Arrays (HSCMA2005) (in printing)
• [Journal Article] Barge-in Free Spoken Dialogue Interface Based on Response Sound Cancellation Using Sound field Control and Microphone Array (2005)
  • Author(s): Shigeki Miyabe, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of Joint Workshop on Hands-Free Speech Communication and Microphone Arrays (HSCMA2005) (in printing)
• [Journal Article] Hands-Free Speech Recognition Using Spatial Subtraction Array (2005)
  • Author(s): Yasuaki Ohashi, Koichi Sakamoto, Tsuyoki Nishikawa, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of Joint Workshop on Hands-Free Speech Communication and Microphone Arrays (HSCMA2005) (in printing)
• [Journal Article] 音声対話によるソフトウェアサポートタスクのための効率的な確認戦略 (2005)
  • Author(s): 翠輝久, 駒谷和範, 清田陽司, 河原達也
  • Journal Title: 電子情報通信学会論文誌 Vol.J88-DII, No.3 Pages: 499-508
• [Journal Article] Incorporating dialogue context and topic clustering in out-of-domain detection (2005)
  • Author(s): I.R.Lane, T.Kawahara
  • Journal Title: In Proc. IEEE-ICASSP (accepter for publication)
• [Journal Article] A new ASR evaluation measure and minimum Bayes-risk decoding for open-domain speech understanding (2005)
  • Author(s): H.Nanjo, T.Kawahara
  • Journal Title: In Proc. IEEE-ICASSP (accepter for publication)
• [Journal Article] Generalized statistical modeling of pronunciation variations using variable-length phone context (2005)
  • Author(s): Y.Akita, T.Kawahara
  • Journal Title: In Proc. IEEE-ICASSP (accepter for publication)
• [Journal Article] Multiple Regression of Log Spectra for In-car Speech Recognition using Multiple Distributed Microphones (2005)
  • Author(s): Weifeng Li, Tetsuya Shinde, Hiroshi Fujimura, Chiyomi Miyajima, Takanori Nishino, Katunobu Itou, Kazuya Takeda, Fumitada
  • Journal Title: IEICE Transactions on Information and Systems Vol.E88-D, No.3 Pages: 384-390
• [Journal Article] CIAIR In-Car Speech Corpus - Influence of the Driving Status (letter) (2005)
  • Author(s): Nobuo Kawaguchi, Shigeki Matsubara, Kazuya Takeda, Fumitada Itakura
  • Journal Title: IEICE Transactions on Information and Systems (in print)
• [Journal Article] Adaptive Log-spectral Regression for In-car Speech Recognition using Multiple Distributed Microphones (letter) (2005)
  • Author(s): Weifeng Li, Kazuya Takeda, Fumitada
  • Journal Title: IEEE Signal Processing Letters (in print)
• [Journal Article] Speech Recognition using Finger Tapping Timings (letter) (2005)
  • Author(s): Hiromitsu Ban, Chiyomi Miyajima, Katsunobu Itou, Kazuya Takeda, Fumitada Itakura
  • Journal Title: IEICE Trans.Inf. and Syst. vol.E88-D, No.3 Pages: 667-670
• [Journal Article] Adaptive Nonlinear Regression for In-car Speech Recognition using Multiple Distributed Microphones (2005)
  • Author(s): Weifeng Li, Chiyomi MIYAJIMA, Takanori NISHINO, Katunobu ITOU, Kazuya TAKEDA, Fumitada ITAKURA
  • Journal Title: IEICE Transactions on Information and Systems, IEICE-A (E) (accepted for publication)
• [Journal Article] Analysis of a large in-car speech corpus and its application to the multimodel ASR (2005)
  • Author(s): Hiroshi Fujimura, Chiyomi Miyajima, Katsunobu Itou, Kazuya Takeda, Fumitada Itakura
  • Journal Title: Proc. of International Conference on Acoustic Speech and Signal Processing (in printing)
• [Journal Article] Spatial coding based on the extraction of moving sound sources in wavefield synthesis (2005)
  • Author(s): Toshiyuki Kimura, Kazuhiko Kakehi, Kazuya Takeda, Fumitada Itakura
  • Journal Title: Proc. of International Conference on Acoustic Speech and Signal Processing (in printing)
• [Journal Article] Two-stage noise spectra estimation and regression based in-car speech recognition using single distant microphone (2005)
  • Author(s): Weifeng Li, Katsunobu Itou, Kazuya Takeda
  • Journal Title: Proc. of International Conference on Acoustic Speech and Signal Processing (in printing)
• [Journal Article] SNR and local noise power estimations based on Gaussinan mixture modeling on the log-power domain (2005)
  • Author(s): Kazuya Takeda, Tran Dat, Hiroshi Fujimura, Fumitada Itakura
  • Journal Title: Proc. of International Conference on Acoustic Speech and Signal Processing (in printing)
• [Journal Article] Generalized Gamma modeling of speech and its online estimation for speech enhancement (2005)
  • Author(s): Tran Dat, Kazuya Takeda, Fumitada Itakura
  • Journal Title: Proc. of International Conference on Acoustic Speech and Signal Processing (in printing)
• [Journal Article] ケプストラム分析を用いた室内伝達関数のモデル化の検討 (2005)
  • Author(s): 斎藤文訓, 西野隆典, 伊藤克亘, 武田一哉
  • Journal Title: 電子情報通信学会技術研究報告 EA2004-139 Pages: 19-24
• [Journal Article] 運転行動信号に含まれる個人性のモデル化 (2005)
  • Author(s): 小澤晃史, 脇田敏裕, 宮島千代美, 伊藤克亘, 武田一哉
  • Journal Title: 電子情報通信学会技術研究報告 HCS2004-40, HIP2004-95 Pages: 17-22
• [Journal Article] Speech enhancement based on a MAP-log spectral magnitude estimation using the gamma prior (2005)
  • Author(s): T.H.Dat, K.Takeda, F.Itakura
  • Journal Title: 日本音響学会講演論文集 1-5-11 Pages: 21-22
• [Journal Article] Blind Detection of CLT Disobeying Frequency Bind for Audio Source Separation by Fixed-Point ICA (2004)
  • Author(s): Raj Kishore Prasad, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: 18th International Congress on Acoustics (ICA2004) vol.IV Pages: 3151--3154
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Adaptive algorithm of itarative inverse filter relaxation to acoustic fluctuation in sound reproduction system (2004)
  • Author(s): Yosuke Tatekura, Yu Nagata, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: 18th International Congress on Acoustics (ICA2004) vol.IV Pages: 3163-3166
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Interface for Barge-in Free Spoken Dialogue System Using Adaptive Sound Field Control and Microphone Array (2004)
  • Author(s): Tatsunori Asai, Yoichi Hinamoto, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: 18th International Congress on Acoustics (ICA2004) vo.I Pages: 755-758
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Overdetermined Blind Separation for Convolutive Mixtures of Speech Based on Multistage ICA using Subarray Processing (2004)
  • Author(s): Tsuyoki Nishikawa, Hiroshi Abe, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2004) Vol.I Pages: 225-228
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Blind Separation of Binaural Sound Mixtures Using SIMO-Model-Based Independent Component Analysis (2004)
  • Author(s): Tomoya Takatani, Tsuyoki Nishikawa, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2004) Vol.IV Pages: 113-116
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Perceptual Evaluation of Quality Deterioration Owing to Prosody Modification (2004)
  • Author(s): Kazuki Adachi, Tomoki Toda, Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC2004) Vol.VI Pages: 2159-2162
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Audible (Normal) Speech and Inaudible Murmur Recognition Using NAM Microphone (2004)
  • Author(s): Panikos Heracleous, Yoshitaka Nakajima, Akinobu Lee, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of the 12th European Signal Processing Conference (EUSIPCO2004) 1 Pages: 329-332
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Evaluation of Blind Separation and Deconvolution for Binaural-Sound Mixtures Using SIMO-Model-Based ICA (2004)
  • Author(s): Hiroaki Yamajo, Hiroshi Saruwatari, Tomoya Takatani, Tsuyoki Nishikawa, Kiyohiro Shikano
  • Journal Title: Proceedings of the 12th European Signal Processing Conference (EUSIPCO2004) 1 Pages: 1709-1712
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] On-line adaptive algorithm to acoustic fluctuation for inverse filter relaxation in sound reproduction system (2004)
  • Author(s): Yosuke Tatekura, Shigefumi Urata, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of the 12th European Signal Processing Conference (EUSIPCO2004) 1 Pages: 1765-1768
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Stable and Low-Distortion Algorithm Based on Overdetermined Blind Separation for Convolutive Mixtures of Speech (2004)
  • Author(s): Tsuyoki Nishikawa, Hiroshi Saruwatari, Kiyohiro Shikano, Atsunobu Kaminuma
  • Journal Title: 5th International Symposium on Independent Component Analysis and Blind Signal Separation (ICA2004) 1 Pages: 881-888
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Evaluation of Multistage SIMO-Model-Based Blind Source Separation Combining Frequency-Domain ICA and Time-Domain ICA (2004)
  • Author(s): Satoshi Ukai, Hiroshi Saruwatari, Tomoya Takatani, Kiyohiro Shikano, Ryo Mukai, Hiroshi Sawada
  • Journal Title: 5th International Symposium on Independent Component Analysis and Blind Signal Separation (ICA2004) 1 Pages: 626-633
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Single Channel Speech Enhancement : MAP Estimation Using GGD Prior Under Blind Setup (2004)
  • Author(s): Raj Kishore Prasad, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: 5th International Symposium on Independent Component Analysis and Blind Signal Separation (ICA2004) 1 Pages: 873-880
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Noise Estimation Using Negentropy Based Voice-Activity Detector (2004)
  • Author(s): Raj Kishore Prasad, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: 2004 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS 2004) II Pages: 149-152
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Automatic audio archiving system for panel discussions (2004)
  • Author(s): Y.Akita, M.Hasegawa, T.Kawahara
  • Journal Title: In Proc. IEEE Int'l Conf. Multimedia and Expo (ICME) 1 Pages: 1-4
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Dependency structure analysis and sentence boundary detection in spontaneous Japanese (2004)
  • Author(s): K.Shitaoka, K.Uchimoto, T.Kawahara, H.Isahara
  • Journal Title: In Proc. COLING 1 Pages: 1107-1113
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Efficient confirmation strategy for large-scale text retrieval systems with spoken dialogue interface (2004)
  • Author(s): K.Komatani, T.Misu, T.Kawahara, H.G.Okuno
  • Journal Title: In Proc. COLING 1 Pages: 1100-1106
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Confirmation strategy for document retrieval systems with spoken dialog interface (2004)
  • Author(s): T.Misu, K.Komatani, T.Kawahara
  • Journal Title: In Proc. ICSLP 1 Pages: 45-48
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Dependency structure analysis and sentence boundary detection in spontaneous Japanese (2004)
  • Author(s): K.Shitaoka, K.Uchimoto, T.Kawahara, H.Isahara
  • Journal Title: In Proc. ICSLP 1 Pages: 1353-1356
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Practical use of English pronunciation system for Japanese students in the CALL classroom (2004)
  • Author(s): Y.Tsubota, M.Dantsuji, T.Kawahara
  • Journal Title: In Proc. ICSLP 1 Pages: 1689-1692
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Automatic extraction of key sentences from oral presentations using statistical measure based on discourse markers (2004)
  • Author(s): T.Kitade, H.Nanjo, T.Kawahara
  • Journal Title: In Proc. ICSLP 1 Pages: 2169-2172
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Topic classification and verification modeling for out-of-domain utterance detection (2004)
  • Author(s): I.R.Lane, T.Kawahara, T.Matsui, S.Nakamura
  • Journal Title: In Proc. ICSLP 1 Pages: 2197-2200
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Example-based training of dialogue planning incorporating user and situation models (2004)
  • Author(s): S.Ueno, I.R.Lane, T.Kawahara
  • Journal Title: In Proc. ICSLP 1 Pages: 2837-2840
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Automatic transformation of lecture transcription into document style using statistical framework (2004)
  • Author(s): K.Shitaoka, H.Nanjo, T.Kawahara
  • Journal Title: In Proc. ICSLP 1 Pages: 2881-2884
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Example-based Spoken Dialogue System with Online Example Augmentation (2004)
  • Author(s): H.Murao, N.Kawaguchi, S.Matsubara, Y.Yamaguchi, K.Takeda, Y.Inagaki
  • Journal Title: Proc. of International Conference on Spoken Language Processing, (INTERSPEECH/ICSLP 2004, Cheju Korea) FrA1502p.15 Pages: 3073-3076
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Optimizing Regression for in-car Speech Recognition using Multiple Distributed Microphones (2004)
  • Author(s): W.Li, K.Takeda, F.Itakura
  • Journal Title: Proc. of International Conference on Spoken Language Processing, (INTERSPEECH/ICSLP 2004, Cheju Korea) FrA1502p.15 Pages: 2689-2692
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Audio-Visual Speaker Localization for Car Navigation Systems (2004)
  • Author(s): X.Zhang, K.Takeda, J.Hansen, T.Maeno
  • Journal Title: Proc. of International Conference on Spoken Language Processing, (INTERSPEECH/ICSLP 2004, Cheju Korea) Spec3603p.4 Pages: 2501-2504
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] CIAIR In-Car Speech Database (2004)
  • Author(s): N.Kawaguchi, S.Matsubara, Y.Yamaguchi, K.Takeda, F.Itakura
  • Journal Title: Proc. of International Conference on Spoken Language Processing FrA2702p.18 Pages: 2789-2792
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Analysis of In-car speech recognition experiments using a large-scale multi-mode dialogue corpus (2004)
  • Author(s): K.Fujimura, K.Itou, K.Takeda, F.Itakura
  • Journal Title: Proc. of International Conference on Spoken Language Processing Spec4001o.2 Pages: 2313-2316
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Speech recognition using synchronization between speech and figre tapping (2004)
  • Author(s): H.Bann, C.Miyajima, K.Itou, K.Takeda, F.Itakura
  • Journal Title: Proc. of International Conference on Spoken Language Processing ThC2501o.1 Pages: 2289-2292
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Speech enhancement based on magnitude estimation using the Gamma prior (2004)
  • Author(s): Tran Huy Dat, Weifang Lee, Kazuya Takeda, Fumitada Itakura
  • Journal Title: Proc. of International Conference on Spoken Language Processing FrA1502p.16 Pages: 2693-2696
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 分散して蓄積されたデータを利用する音響モデル学習システム (2004)
  • Author(s): 武田一哉, 伊藤克亘, 河原達也, 鹿野清宏
  • Journal Title: 日本音響学会講演論文集 2-1-25 Pages: 85-86
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 車内対話音声のSNR依存音響モデルの評価 (2004)
  • Author(s): 藤村浩司, 宮島千代美, 伊藤克亘, 武田一哉
  • Journal Title: 日本音響学会講演論文集 3-1-16 Pages: 141-142
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 楽曲検索のための音声対話インタフェース構築に関する検討 (2004)
  • Author(s): 原直, 白勢彩子, 伊藤克亘, 武田一哉
  • Journal Title: 日本音響学会講演論文集 1-P-21 Pages: 203-204
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 音声対話システムユーザの課題達成率に基づく分析 (2004)
  • Author(s): 白勢彩子, 原直, 伊藤克亘, 武田一哉
  • Journal Title: 日本音響学会講演論文集 1-P-24 Pages: 209-210
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 身体的特徴量から推定した頭部伝達関数の評価 (2004)
  • Author(s): 井上直哉, 木村敏幸, 西野隆典, 伊藤克亘, 武田一哉
  • Journal Title: 日本音響学会講演論文集 3-P-5 Pages: 663-664
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 虚像法を用いた両耳室内インパルス応答の推定 (2004)
  • Author(s): 斉藤文訓, 西野隆典, 伊藤克亘, 武田一哉
  • Journal Title: 日本音響学会講演論文集 3-P-22 Pages: 697-698
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 位置情報による移動音源再現手法の主観的影響 (2004)
  • Author(s): 木村敏幸, 筧一彦, 武田一哉, 板倉文忠
  • Journal Title: 日本音響学会講演論文集 3-P-29 Pages: 711-712
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 音声情報処理の観点から見た室内音場の評価について (2004)
  • Author(s): 武田一哉, 小村道昭, 清水泰博, 梶田将司, 板倉文忠
  • Journal Title: 建築音響研究会資料 AA2004-24 Pages: 1-6
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 音声対話による楽曲検索システム (2004)
  • Author(s): 原直, 白勢彩子, 宮島千代美, 伊藤克亘, 武田一哉
  • Journal Title: 情報処理学会研究報告 2004-SLP-53(6) Pages: 31-36
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] マイクロホンアレーを用いた自由聴点音場再生システムに関する理論的検討 (2004)
  • Author(s): 水野渉, 木村敏幸, 西野隆典, 武田一哉
  • Journal Title: 電子情報通信学会技術研究報告 EA2004-118 Pages: 7-12
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] 音声対話インタフェースの長期利用時における学習効果の評価 (2004)
  • Author(s): 原直, 白勢彩子, 宮島千代美, 伊藤克亘, 武田一哉
  • Journal Title: 情報処理学会研究報告 2005-SLP-55(4) Pages: 17-22
  • Description: 「研究成果報告書概要(和文)」より
• [Journal Article] Robots That Can Hear, Understand and Talk (2004)
  • Author(s): Rajkishore Prasad, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Advanced Robotics Vol.18, No.5 Pages: 451-564
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Negentropy based voice-activity detection for noise estimation in very low SNR condition (2004)
  • Author(s): Rajkishore Prasad, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: IEICE Electronics Express (ELEX) vol.1, no.16 Pages: 495-500
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Overdetermined Blind Separation of Acoustic Signals Based on MISO-Constrained Frequency-Domain ICA (2004)
  • Author(s): Tsuyoki Nishikawa, Hiroshi Abe, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: 18th International Congress on Acoustics (ICA2004) vol.IV Pages: 3143-3146
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Real-Time Word Confidence Scoring using Local Posterior probabilities on Tree Trellis Search (2004)
  • Author(s): Akinobu Lee, Kiyohiro Shikano, Tatsuya Kawahara
  • Journal Title: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2004) Vol.I Pages: 793-796
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Public Speech-Oriented Guidance System with Adult and Child Discrimination Capability (2004)
  • Author(s): Ryuichi Nisimura, Akinobu Lee, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2004) Vol.I Pages: 433-436
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Noice Robust Real World Spoken Dialogue System using GMM Based Rejection of Unintended Inputs (2004)
  • Author(s): Akinobu Lee, Keisuke Nakamura, Ryuichi Nisimura, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of 8th International Conference on Spoken Language Processing (ICSLP2004) TuA1302p-2, Vol.I Pages: 173-176
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Non-Audible Murmur (NAM) Speech Recognition Using a Stethoscopic NAM Microphone (2004)
  • Author(s): Panikos Heracleous, Yoshitaka Nakajima, Akinobu Lee, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of 8th International Conference on Spoken Language Processing (ICSLP2004) WeC2102p-6, vol.II Pages: 1469-1472
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Robust Speech Recognition with Spectral Subtraction in Low SNR (2004)
  • Author(s): Randy Gomez, Akinobu Lee, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of 8th International Conference on Spoken Language Processing (ICSLP2004) ThB1702p-10, vol.III Pages: 2077-2080
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Recent Progress of Open-Source LVCSR Engine Julius and Japanese Model Repository (2004)
  • Author(s): Tatsuya Kawahara, Akinobu Lee, Kazuya Takeda, Katsunobu Itou, Kiyohiro Shikano
  • Journal Title: Proceedings of 8th International Conference on Spoken Language Processing (ICSLP2004) Spec4402p-6, vol.IV Pages: 3069-3072
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Method for determining sound localization by auditory masking (2004)
  • Author(s): Kazuhiko Uchida, Takanori Nishino, Kazuya Takeda, Fumitada Itakura
  • Journal Title: Acoustical Science and Technology Vol.25, No.6 Pages: 480-482
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] Robust SNR estimation of noisy speech based on Gaussian mixtures modeling on log-power domain (2004)
  • Author(s): Tran Huy Dat, Kazuya Takeda, Fumitada Itakura
  • Journal Title: COST278 and ISCA Tutorial and Research Workshop (ITRW) on Robustness Issues in Conversational Interaction 1 Pages: 1-4
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] AURORA-2J : Japanese speech data collection for performance evaluation of speech recognition in noise (2004)
  • Author(s): Satoshi Nakamura, Kazumasa Yamamoto, Kazuya Takeda, Shingo Kuroiwa, Norihide Kitaoka, Takeshi Yamada, Mitsunori Mizumachi, Takanobu Nishiura, Masakiyo Fujimoto, Akira Saso, Toshiki Endo
  • Journal Title: International Conference on Speech and Language Technology/Oriental-COCOSDA 2004 (in printing)
  • Description: 「研究成果報告書概要(欧文)」より
• [Journal Article] 実環境における頑健な音声認識のための音韻モデルの教師なし話者適応 (2004)
  • Author(s): 山出慎吾, 馬場朗, 芳澤伸一, 李晃伸, 猿渡洋, 鹿野清宏
  • Journal Title: 電子情報通信学会論文誌 Vol.J87-D-II, No.4 Pages: 933-941
• [Journal Article] Overdetermined Blind Separation for Real Convolutive Mixtures of Speech Based on Multistage ICA Using Subarray Processing (2004)
  • Author(s): Tsuyoki Nishikawa, Hiroshi Abe, Hiroshi Saruwatari, Kiyohiro Shikano, Atsunobu Kaminuma
  • Journal Title: EICE Trans.Fundamentals Vol.E87-A Pages: 1924-1932
• [Journal Article] High-Fidelity Blind Separation of Acoustic Signals Using SIMO-Model-Based Independent Component Analysis (2004)
  • Author(s): Tomoya Takatani, Tsuyoki Nishikawa, Hiroshi Saruwatari, Kiyohiro S
  • Journal Title: IEICE Trans.Fundamentals Vol.E87-A, No.8 Pages: 2063-2072
• [Journal Article] 非可聴つぶやき認識 (2004)
  • Author(s): 中島淑貴, 柏岡秀紀, ニックキャンベル, 鹿野清宏
  • Journal Title: 電子情報通信学会論文誌 Vol.J87-D-II, No.9 Pages: 1757-1764
• [Journal Article] Comparison between SIMO-ICA with least squares criterion and SIMO-ICA with information-geometric learning (2004)
  • Author(s): Tomoya Takatani, Tsuyoki Nishikawa, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: 18th International Congress on Acoustics (ICA2004) Vol.I Pages: 329-332
• [Journal Article] Rapid EM Training based on Model-Integration (2004)
  • Author(s): Shinichi Yoshizawa, Kiyohiro Shikano
  • Journal Title: Proceedings of 8th International Conference on Spoken Language Processing (ICSLP2004) TuC2101p-2, vol.I Pages: 649-652
• [Journal Article] Interface For Barge-in Free Spoken Dialogue System Using Adaptive Sound Field Control (2004)
  • Author(s): Tatsunori Asai, Shigeki Miyabe, Hiroshi Saruwatari, Kiyohiro Shikano
  • Journal Title: Proceedings of 8th International Conference on Spoken Language Processing (ICSLP2004) FrA1502p-9, vol.IV Pages: 2665-2668
• [Journal Article] 音声対話システムにおける適応的な応答生成を行うためのユーザモデル (2004)
  • Author(s): 駒谷和範, 上野晋一, 河原達也, 奥乃博
  • Journal Title: 電子情報通信学会論文誌 Vol.J87-DII, No.10 Pages: 1921-1928
• [Journal Article] Practical use of autonomous English pronunciation learning system for Japanese students (2004)
  • Author(s): Y.Tsubota, M.Dantsuji, T.Kawahara
  • Journal Title: n Proc. InSTIL/ICALL - NLP and Speech Technologies in Advanced Language Learning Systems 1 Pages: 139-142
• [Journal Article] Measurement of the Head Related Transfer Function using the Spark Noise (2004)
  • Author(s): Takanori NISHINO, Seiichiro HOSOE, Kazuya TAKEDA, Fumitada ITAKURA
  • Journal Title: Proc. Of International Conference on Acoustics 2004 ICA2004, Tu5. D.1 Pages: II-1437-II-1438
• [Journal Article] In-car speech recognition experiments using a large-scale multi-mode dialogue corpus (2004)
  • Author(s): Hiroshi FUJIMURA, Katsunobu ITOU, Kazuya TAKEDA, Fumitada ITAKURA
  • Journal Title: Proc. Of International Conference on Acoustics 2004 ICA2004, Th2. H.1 Pages: IV-2583-IV-2586
• [Journal Article] Subjective assessments for the effect of the number od channel signals on the sound field reproduction used in wavefield synthesis (2004)
  • Author(s): Toshiyuki KIMURA, Kazuhiko KAKEHI, Kazuya TAKEDA, Fumitada ITAKURA
  • Journal Title: Proc. Of International Conference on Acoustics 2004 ICA2004, Th.P1.17 Pages: IV-3159-IV3162
• [Journal Article] Biometric Identification Using Driving Behavioral Signals (2004)
  • Author(s): Kei Igarashi, Chiyomi Miyajima, Katsunobu Itou, Kazuya Takeda, Fumitada Itakura, Huseyin Abut
  • Journal Title: The 2004 IEEE International Conference on Mulitdedia and Expo (ICME' 2004) 1 Pages: 1-4
• [Journal Article] An Advanced Japanese Speech Corpus for In-car Spoken Dialogue Research (2004)
  • Author(s): Yuki Irie, Nobuo Kawaguchi, Shigeki Matsubara, Itsuki Kishida, Yukiko Yamaguchi, Kazuya Takeda, Fumitada Itakura, Yasuyoshi Inagaki
  • Journal Title: Proc. of International Coordinating Committee on Speech Databases and Speech I/O System Assessment (O-COCOSDA 2004) 1 Pages: 1-8
• [Journal Article] 事典コーパスを用いた単語階層関係の統計的解析 (2004)
  • Author(s): 大石康智, 伊藤克亘, 武田一哉, 藤井敦, 板倉文忠
  • Journal Title: 第3回情報科学技術フォーラム(FIT2004) LF-001 Pages: 75-78
• [Journal Article] 運転行動信号に含まれる個人性に関する検討 (2004)
  • Author(s): 小澤晃史, 伊藤克亘, 武田一哉, 脇田敏裕, 板倉文忠
  • Journal Title: 第3回情報科学技術フォーラム(FIT2004) LK-004 Pages: 247-250
• [Book] DSP in Mobile and Vehicular Systems (2004)
  • Author(s): Huseyin Abut, John Hansen, Kazuya Takeda (Eds.)
  • Total Pages: 313
  • Publisher: Springer Publisher