메뉴 건너뛰기




Volumn 2015-January, Issue , 2015, Pages 3214-3218

A time delay neural network architecture for efficient modeling of long temporal contexts

Author keywords

Acoustic modeling; Recurrent neural networks; Time delay neural networks

Indexed keywords

FEEDFORWARD NEURAL NETWORKS; LEARNING ALGORITHMS; NEURAL NETWORKS; RECURRENT NEURAL NETWORKS; SPEECH COMMUNICATION; TIME DELAY;

EID: 84959115289     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (1131)

References (32)
  • 3
    • 84935413199 scopus 로고
    • Modular construction of time-delay neural networks for speech recognition
    • A. Waibel, "Modular construction of time-delay neural networks for speech recognition, " Neural computation, vol. 1, no. 1, pp. 39-46, 1989.
    • (1989) Neural Computation , vol.1 , Issue.1 , pp. 39-46
    • Waibel, A.1
  • 16
    • 0019053271 scopus 로고
    • Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences
    • S. B. Davis and P. Mermelstein, "Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences, " IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 28, no. 4, pp. 357-366, 1980.
    • (1980) IEEE Transactions on Acoustics, Speech and Signal Processing , vol.28 , Issue.4 , pp. 357-366
    • Davis, S.B.1    Mermelstein, P.2
  • 21
    • 84976219984 scopus 로고    scopus 로고
    • An i-vector based time delay neural network architecture for far field recognition
    • V. Peddinti, G. Chen, D. Povey, and S. Khudanpur, "An i-vector based time delay neural network architecture for far field recognition, " in Proceedings of INTERSPEECH, 2015. [Online]. Available: http: //www. danielpovey. com/files/ 2015 interspeech aspire. pdf
    • (2015) Proceedings of INTERSPEECH
    • Peddinti, V.1    Chen, G.2    Povey, D.3    Khudanpur, S.4
  • 22
    • 84959176266 scopus 로고    scopus 로고
    • Semi-supervised maximum mutual information training of deep neural network acoustic models
    • V. Manohar, D. Povey, and S. Khudanpur, "Semi-supervised maximum mutual information training of deep neural network acoustic models, " in Proceedings of INTERSPEECH, 2015. [Online]. Available: http: //www. danielpovey. com/files/ 2015 interspeech entropy. pdf
    • (2015) Proceedings of INTERSPEECH
    • Manohar, V.1    Povey, D.2    Khudanpur, S.3
  • 23
    • 84959118622 scopus 로고    scopus 로고
    • Audio augmentation for speech recognition
    • T. Ko, V. Peddinti, D. Povey, and S. Khudanpur, "Audio augmentation for speech recognition, " in Proceedings of INTERSPEECH, 2015. [Online]. Available: http: //www. danielpovey. com/files/2015 interspeech augmentation. pdf
    • (2015) Proceedings of INTERSPEECH
    • Ko, T.1    Peddinti, V.2    Povey, D.3    Khudanpur, S.4
  • 24
    • 84959101589 scopus 로고    scopus 로고
    • Pronunciation and silence probability modeling for ASR
    • G. Chen, H. Xu, M. Wu, D. Povey, and S. Khudanpur, "Pronunciation and silence probability modeling for ASR, " in Proceedings of INTERSPEECH, 2015. [Online]. Available: http: //www. danielpovey. com/files/2015 interspeech silprob. pdf
    • (2015) Proceedings of INTERSPEECH
    • Chen, G.1    Xu, H.2    Wu, M.3    Povey, D.4    Khudanpur, S.5
  • 30
    • 84946076428 scopus 로고    scopus 로고
    • Ted-lium: An automatic speech recognition dedicated corpus
    • A. Rousseau, P. Deléglise, and Y. Estève, "Ted-lium: An automatic speech recognition dedicated corpus. " in LREC, 2012, pp. 125-129.
    • (2012) LREC , pp. 125-129
    • Rousseau, A.1    Deléglise, P.2    Estève, Y.3
  • 32
    • 84959118000 scopus 로고    scopus 로고
    • The fisher corpus: A resource for the next generations of speech-to-text
    • C. Cieri, D. Miller, and K. Walker, "The fisher corpus: A resource for the next generations of speech-to-text. " in LREC, vol. 4, 2004, pp. 69-71.
    • (2004) LREC , vol.4 , pp. 69-71
    • Cieri, C.1    Miller, D.2    Walker, K.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.