A initial attempt on task-specific adaptation for deep neural network-based large vocabulary continuous speech recognition

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 3, Issue , 2012, Pages 2573-2576

  Xiao, Yeming ^a   Zhang, Zhen ^a   Cai, Shang ^a   Pan, Jielin ^a   Yan, Yonghong ^a  

^a INSTITUTE OF GEOLOGY AND GEOPHYSICS   (China)

Author keywords

Deep neural network; LVCSR; Pre training; Speaker adaptation

Indexed keywords

AUTOMATIC SPEECH RECOGNITION SYSTEM; DEEP NEURAL NETWORKS; HIDDEN MARKOV MODEL(HMM); HYBRID ARTIFICIAL NEURAL NETWORK; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LVCSR; PRE-TRAINING; SPEAKER ADAPTATION;

CONTINUOUS SPEECH RECOGNITION; HIDDEN MARKOV MODELS; TELEPHONE SYSTEMS;

NEURAL NETWORKS;

EID: 84878535870     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Gauvain, J.L. and C.H. Lee, Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. Speech and Audio Processing, IEEE Transactions on, 1994. 2(2): p. 291-298.
2. Leggetter, C. and P. Woodland, Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer speech and language, 1995. 9(2): p. 171.
3. Rabiner, L., A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 1989. 77(2): p. 257-286.
4. Neto, J.P., C. Martins, and L.B. Almeida. Speaker-adaptation in a hybrid HMM-MLP recognizer. in Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on. 1996.
5. Abrash, V. Mixture Input Transformations for Adaptation of Hybrid Connectionist Speech Recognizers. Eurospeech. 1997.
6. Kershaw, D., T. Robinson, and S. Renals. The 1995 ABBOT LVCSR system for multiple unknown microphones. 1996: IEEE.
7. Renals, S., et al., Connectionist probability estimators in HMM speech recognition. Speech and Audio Processing, IEEE Transactions on, 1994. 2(1): p. 161-174.
8. Bourlard, H. and N. Morgan, Connectionist speech recognition: a hybrid approach. 1994: Springer.
9. Bourlard, H., et al. CDNN: a context dependent neural network for continuous speech recognition. in Acoustics, Speech, and Signal Processing, 1992.
10. Dahl, G., et al., Context-Dependent Pre-trained Deep Neural Networks for Large Vocabulary Speech Recognition. Audio, Speech, and Language Processing, IEEE Transactions on, 2010(99)
11. Seide, F., G. Li, and D. Yu. Conversational Speech Transcription Using Context-Dependent Deep Neural Networks. 2011.
12. Mohamed, A., G. Dahl, and G. Hinton, Acoustic Modeling using Deep Belief Networks. Audio, Speech, and Language Processing, IEEE Transactions on, 2011(99): p. 1-1.
13. Bourlard, H., Y. Konig, and N. Morgan, A training algorithm for statistical sequence recognition with applications to transitionbased speech recognition. Signal Processing Letters, IEEE, 1996. 3(7): p. 203-205.
14. Yu, D. and L. Deng, Deep Learning and Its Applications to Signal and Information Processing [Exploratory DSP]. Signal Processing Magazine, IEEE, 2011. 28(1): p. 145-154.
15. Seide, F., et al., Feature engineering in context-dependent deep neural networks for conversational speech transcription. 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).
16. Wilson, D.R. and T.R. Martinez. The need for small learning rates on large problems. In Proceedings of the 2001 International Joint Conference on Neural Networks (IJCNN'01), 115-119.