論文

• Ryan Price, Kenichi Iso, Koichi Shinoda. Wise Teachers Train Better DNN Acoustic Models, EURASIP Journal on Audio Speech and Music Processing, Springer International Publishing Ltd, 10, pp. 1-19, Apr. 2016.  公式リンク  
  

国際会議発表 (査読有り)

• Ryan Price, Kenichi Iso, Koichi Shinoda. Speaker Adaptation of Deep Neural Networks Using a Hierarchy of Output Layers, SLT 2014 (2014 IEEE Spoken Language Technology Workshop), Proc. Spoken Language Technology (SLT) Workshop, pp. 153-158, Dec. 2014.
• Ryan Price, Sangeeta Biswas, Koichi Shinoda. Combining Deep Speaker Specific Representations with GMM-SVM for Speaker Verification, INTERSPEECH2013, INTERSPEECH2013, pp. 2788-2792, Aug. 2013.  公式リンク  
  

国内会議発表 (査読なし・不明)

• Devin Hoesen, Ryan Price, Puji Lestari Dessi, Koichi Shinoda. A DNN-Based ASR System for the Indonesian Language, ASJ (Acoustical Society of Japan) 2015 Autumn Meeting, Proc. ASJ 2015 Autumn Meeting, pp. 5-6, Sept. 2015.
• 松山祐輔, Ryan Price, 篠田浩一. 活性化関数のパラメータ制御を用いた LSTM による音声認識, 平成２７年度日本音響学会秋季研究発表会, 日本音響学会2015年秋季研究発表会講演論文集, pp. 1-2, Sept. 2015.
• Ryan Price, Koichi Shinoda, Sangeeta Biswas. Fusing deep speaker specific features and MFCC for robust speaker verification, SLP2013, IPSJ SIG technical reports, Vol. 2013-SLP-97, No. 3, pp. 1-7, July 2013.
• Ryan Price, Koichi Shinoda. Speaker verication using deep speaker-discriminative representations, 日本音響学会 2013年 春季研究発表会, 2013 Spring Meeting ASJ, pp. 81-82, Mar. 2013.

学位論文

• Leveraging Better Training Targets for Deep Neural Network Acoustic Models in Speech Recognition,  Exam Summary,  博士（学術）,  Tokyo Institute of Technology,  2016/09/20,   
• Leveraging Better Training Targets for Deep Neural Network Acoustic Models in Speech Recognition,  Summary,  博士（学術）,  Tokyo Institute of Technology,  2016/09/20,   
• Leveraging Better Training Targets for Deep Neural Network Acoustic Models in Speech Recognition,  Thesis,  博士（学術）,  Tokyo Institute of Technology,  2016/09/20,   

[ BibTeX 形式で保存 ]    [ 論文・著書をCSV形式で保存 ]    [ 特許をCSV形式で保存 ]