메뉴 건너뛰기




Volumn 2015-August, Issue , 2015, Pages 4300-4304

An investigation into speaker informed DNN front-end for LVCSR

Author keywords

bias adaptation; deep neural network; speaker adaptation; speaker informed training; speech recognition

Indexed keywords

AUDIO SIGNAL PROCESSING; CODES (SYMBOLS); HYBRID SYSTEMS; SPEECH COMMUNICATION; SPEECH PROCESSING; SPEECH RECOGNITION;

EID: 84946036535     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178782     Document Type: Conference Paper
Times cited : (18)

References (25)
  • 2
    • 84865785753 scopus 로고    scopus 로고
    • Improved bottleneck features using pretrained deep neural networks
    • August, International Speech Communication Association
    • D. Yu and M. Seltzer, Improved bottleneck features using pretrained deep neural networks, in Interspeech. August 2011, International Speech Communication Association
    • (2011) Interspeech
    • Yu, D.1    Seltzer, M.2
  • 3
    • 84865801985 scopus 로고    scopus 로고
    • Conversational speech transcription using context-dependent deep neural networks
    • F. Seide, G. Li, and D. Yu, Conversational speech transcription using context-dependent deep neural networks, in INTERSPEECH, 2011, pp. 437-440
    • (2011) INTERSPEECH , pp. 437-440
    • Seide, F.1    Li, G.2    Yu, D.3
  • 6
    • 79959849500 scopus 로고    scopus 로고
    • Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems
    • B. Li and K. C. Sim, Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems., in INTERSPEECH, 2010, pp. 526-529
    • (2010) INTERSPEECH , pp. 526-529
    • Li, B.1    Sim, K.C.2
  • 7
    • 34548012893 scopus 로고    scopus 로고
    • Linear hidden transformations for adaptation of hybrid ANN/HMM models
    • Intrinsic Speech Variations
    • R. Gemello, F. Mana, S. Scanzio, P. Laface, and R. D. Mori, Linear hidden transformations for adaptation of hybrid ANN/HMM models, Speech Communication, vol. 49, no. 1011, pp. 827-835, 2007, Intrinsic Speech Variations
    • (2007) Speech Communication , vol.49 , Issue.1011 , pp. 827-835
    • Gemello, R.1    Mana, F.2    Scanzio, S.3    Laface, P.4    Mori, R.D.5
  • 11
    • 84905269643 scopus 로고    scopus 로고
    • Using neural network frontends on far field multiple microphones based speech recognition
    • Florence, Italy, May
    • Y. Liu, P. Zhang, and T. Hain, Using neural network frontends on far field multiple microphones based speech recognition, in ICASSP2014-Speech and Language Processing (ICASSP2014-SLTC), Florence, Italy, May 2014
    • (2014) ICASSP2014-Speech and Language Processing (ICASSP2014-SLTC)
    • Liu, Y.1    Zhang, P.2    Hain, T.3
  • 12
    • 84874226579 scopus 로고    scopus 로고
    • Adaptation of context-dependent deep neural networks for automatic speech recognition
    • December
    • K. Yao, D. Yu, F. Seide, H. Su, L. Deng, and Y. Gong, Adaptation of context-dependent deep neural networks for automatic speech recognition, in SLT 2012, December 2012
    • (2012) SLT 2012
    • Yao, K.1    Yu, D.2    Seide, F.3    Su, H.4    Deng, L.5    Gong, Y.6
  • 13
    • 84910028538 scopus 로고    scopus 로고
    • Speaker dependent bottleneck layer training forspeaker adaptation in automatic speech recognition
    • R. Doddipatla, M. Hasan, and T. Hain, Speaker dependent bottleneck layer training forspeaker adaptation in automatic speech recognition, in Interspeech 2014, 2014
    • (2014) Interspeech 2014
    • Doddipatla, R.1    Hasan, M.2    Hain, T.3
  • 14
    • 84983119674 scopus 로고    scopus 로고
    • Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models
    • South Lake Tahoe, USA, December
    • P. Swietojanski and S. Renals, Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models, in Proc. IEEE Workshop on Spoken Language Technology, South Lake Tahoe, USA, December 2014
    • (2014) Proc. IEEE Workshop on Spoken Language Technology
    • Swietojanski, P.1    Renals, S.2
  • 15
    • 84910097389 scopus 로고    scopus 로고
    • Analysis of i-vector framework for speaker identification in TV-shows
    • C. Fredouille and D. Charlet, Analysis of i-vector framework for speaker identification in TV-shows, in Proceedings of Interspeech' 14, 2014
    • (2014) Proceedings of Interspeech' 14
    • Fredouille, C.1    Charlet, D.2
  • 18
    • 84858959884 scopus 로고    scopus 로고
    • Maximum kurtosis beamforming with a subspace filter for distant speech recognition
    • K. Kumatani, J. W. McDonough, and B. Raj, Maximum kurtosis beamforming with a subspace filter for distant speech recognition, in ASRU'11, 2011, pp. 179-184
    • (2011) ASRU'11 , pp. 179-184
    • Kumatani, K.1    McDonough, J.W.2    Raj, B.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.