English page

早坂 昇


所属:
大阪電気通信大学 情報通信工学部 情報工学科

職位:
講師

学歴:
2002年 北海道大学工学部電子工学科 卒業
2004年 北海道大学大学院工学研究科 修士課程了
2007年 北海道大学大学院情報科学研究科 博士後期課程了
職歴:
2004年〜2007年 北海道工業大学工学部情報ネットワーク工学科 非常勤講師
2004年〜2007年 北海道ハイテクノロジー専門学校 非常勤講師
2004年〜2007年 北海道大学大学院情報科学研究科 リサーチアシスタント
2007年〜2010年 株式会社レイトロン研究員
2010年〜2013年 大阪大学大学院基礎工学研究科 助教
2013年〜現在   大阪電気通信大学情報通信工学部情報工学科 専任講師
2013年〜現在   大阪大学大学院基礎工学研究科 招へい教員

研究:
音声認識を中心とする音声情報処理に関する研究とその実用化

音声認識デモ:
CategoryのDemoをクリックするとJavaアプレットが立ち上がります.
正常に立ち上がらなかった場合は, CategoryのJavaからインストールしてください.
結果が頻繁に誤ってしまう場合は,ゆっくり発声すると正しく認識されることがあります.
また,現在データの都合により,男性の声のみに対応しております.
お使いのOSやブラウザによっては正しく動作しないことがあります.ご了承ください.

学術論文:
  1. 早坂 昇, 宮永 喜一, "非音声区間拡張マルチコンディション単語モデルの雑音ロバスト性に関する実験的評価," 電気学会論文誌C, vol.132, no.10, pp.1667-1674, 2012.
  2. Noboru Hayasaka, "Isolated word recognition based on combination of multiple noise-robust techniques," ECTI Trans. on Computer and Information Technology, vol.6, no.1, pp.80-87, 2012.
  3. Xin Xu, Noboru Hayasaka, and Yoshikazu Miyanaga, "Robust speech spectra restoration against unspecific noise conditions for pitch detection," IEICE Trans. Fundamentals vol.E91-A, no.3, pp.775-781, 2008.
  4. Kham Khankhavivone, Noboru Hayasaka, Yoshikazu Miyanaga, and Kraisin Songwatana, "Low-cost running spectrum filter for speech recognition using modified frequency response masking technique," Journal of Signal Processing, vol.11, no.3, pp.227-236, 2007.
  5. 早坂 昇, 吉澤 真吾, 宮永 喜一, "推定SNRに基づくスペクトル領域フィルタリングを用いた雑音に頑健な孤立単語音声認識," 電子情報通信学会論文誌D, vol.J89-D, no.10, pp.2296-2304, 2006.
  6. Shingo Yoshizawa, Naoya Wada, Noboru Hayasaka, and Yoshikazu Miyanaga, "Scalable architecture for word HMM-based speech recognition and VLSI implementation in complete system," IEEE Trans. on Circuit and Systems-I, vol.53, no.1, pp.70-77, 2006.
  7. Shingo Yoshizawa, Noboru Hayasaka, Naoya Wada, and Yoshikazu Miyanaga, "VLSI architecture for robust speech recognition systems and its implementation in verification platform," Journal of Robotics and Mechatronics, vol.17, no.4, pp.447-455, 2005.
  8. Naoya Wada, Shingo Yoshizawa, Noboru Hayasaka, and Yoshikazu Miyanaga, "Robust speech feature extraction using RSF/DRA and burst noise skipping," ECTI Trans. on Electrical Engineering, Electronics, and Communications, vol.3, no.2, pp.100-107, 2005.
  9. 早坂 昇, 吉澤 真吾, 和田 直哉, 宮永 喜一, 畑岡 信夫, "ロバスト音声認識とそのLSI化について," 計測自動制御学会論文集, vol.41, no.5, pp.473-480, 2005.
  10. 藤岡 一馬, 早坂 昇, 宮永 喜一, 吉田 則信, "ランニングスペクトルフィルタリングを用いた音声の雑音低減法," 電子情報通信学会論文誌D, vol.J88-D2, no.4, pp.695-703, 2005.
  11. Shingo Yoshizawa, Noboru Hayasaka, Naoya Wada, and Yoshikazu Miyanaga, "Cepstral amplitude range normalization for noise robust speech recognition," IEICE Trans. Inf. Syst., vol.E87-D, no.8, pp.2130-2137, 2004.

国際会議:
  1. Takuya Futagami, Noboru Hayasaka, and Youji Iiguni, "Speaker adaptation using improved MAP estimation with small amount of adaptation data," IEEE Region 10 Conference (TENCON), Paper ID 135, Oct. 2013.
  2. Shuichiro Hirota, Noboru Hayasaka, and Youji Iiguni, "Experimental evaluation of structure of garbage model generated from in-vocabulary words," Int'l Symposium on Communications and Information Technologies (ISCIT), pp.92-97, Oct. 2012.
  3. Yudai Kaneda, Noboru Hayasaka, and Youji Iiguni, "Feature reduction using PCA with multi-condition training for practical speech recognition systems," Int'l Symposium on Communications and Information Technologies (ISCIT), pp.98-103, Oct. 2012.
  4. Ryota Hashimoto, Noboru Hayasaka, and Youji Iiguni, "Log-based frequency warping for speech recognition," Int'l Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), pp.443-446, June 2011.
  5. Noboru Hayasaka, Kham Khankhavivone, Yoshikazu Miyanaga, and Kraisin Songwatana, "New robust speech recognition by using nonlinear running spectrum filter," Int'l Symposium on Communications and Information Technologies (ISCIT), pp.133-136, Oct. 2006.
  6. PeiJu Lin, Takayuki Sugawara, Noboru Hayasaka, and Yoshikazu Miyanaga, "A new e-learning system based on cooperative methods - next-generation extra university-education system," Int'l Symposium on Communications and Information Technologies (ISCIT), pp.727-730, Oct. 2006.
  7. Noboru Hayasaka, Yoshikazu Miyanaga, and Kham Khankhavivone, "Intelligent speech recognition system," Int'l Conference on Soft Computing and Intelligent Systems & Int'l Symposium on Advanced Intelligent Systems (SCIS & ISIS), pp.658-663, Sep. 2006.
  8. Noboru Hayasaka and Yoshikazu Miyanaga, "Spectrum filtering with FRM for robust speech recognition," IEEE Int'l Symposium on Circuits and Systems (ISCAS), pp.3285-3288, May 2006.
  9. Naoya Wada, Noboru Hayasaka, Shingo Yoshizawa, and Yoshikazu Miyanaga, "Direct control on modulations Spectrum for noise-robust speech recognition and spectral subtraction," IEEE Int'l Symposium on Circuits and Systems (ISCAS), pp.2533-2536, May 2006.
  10. Xin Xu, Noboru Hayasaka, Qi Zhu, and Yoshikazu Miyanaga, "Noise robust Chinese speech recognition system for isolate words," IEEE-EURASIP Int'l Workshop on Nonlinear Signal and Image Processing (NSIP), pp.420-425, May 2005.
  11. Noboru Hayasaka and Yoshikazu Miyanaga, "A study of robust speech recognition using FRM filter," IEEE Region 10 Conference (TENCON), pp.80-83, Nov. 2004.
  12. Naoya Wada, Noboru Hayasaka, Shingo Yoshizawa, and Yoshikazu Miyanaga, "Robust speech recognition with feature extraction using combined method of RSF and DRA," Int'l Symposium on Communications and Information Technologies (ISCIT), pp.1001-1004, Oct. 2004.
  13. Shingo Yoshizawa, Naoya Wada, Noboru Hayasaka, and Yoshikazu Miyanaga, "VLSI architecture for HMM-based speech recognition systems and its verification platform," Int'l Symposium on Communications and Information Technologies (ISCIT), pp.700-703, Oct. 2004.
  14. Shingo Yoshizawa, Naoya Wada, Noboru Hayasaka, and Yoshikazu Miyanaga, "Scalable architecture for word HMM-based speech recognition," IEEE Int'l Symposium on Circuits and Systems (ISCAS), pp.417-420, May 2004.
  15. Shingo Yoshizawa, Noboru Hayasaka, Naoya Wada, and Yoshikazu Miyanaga, "Cepstral gain normalization for noise robust speech recognition," IEEE Int'l Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.209-212, May 2004.
  16. Noboru Hayasaka, Naoya Wada, Shingo Yoshizawa, and Yoshikazu Miyanaga, "A robust speech recognition system using FRM running spectrum filtering," Int'l Symposium on Control, Communications and Signal Processing (ISCCSP), pp.401-404, Mar. 2004.
  17. Shingo Yoshizawa, Naoya Wada, Noboru Hayasaka, and Yoshikazu Miyanaga, "Noise robust speech recognition focusing on time variation and dynamic range of speech feature parameters," Int'l Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp.484-487, Dec. 2003.
  18. Shingo Yoshizaw, Noboru Hayasakaa, Atsuya Kageyama, and Yoshikazu Miyanaga, "Development of a dedicated hardware system for noise robust speech recognition using RSF/DRA technique," Int'l Symposium on Communications and Information Technologies (ISCIT), pp.463-466, Sep. 2003.
  19. Naoya Wada, Noboru Hayasaka, Nobuo Hataoka, and Yoshikazu Miyanaga, "Noise robust speech detection/recognition system including RSF/DRA and MFCC," Int'l Symposium on Communications and Information Technologies, pp.455-458 (ISCIT), Sep. 2003.
  20. Noboru Hayasaka, Yoshikazu Miyanaga, and Naoya Wada, "Running spectrum filtering in speech recognition," Int'l Conference on Soft Computing and Intelligent Systems & Int'l Symposium on Advanced Intelligent Systems (SCIS & ISIS), no.210, Oct. 2002.


QLOOKアクセス解析