Hermitian-based Hidden activation functions for adaptation of hybrid HMM/ANN models

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

Volumn 3, Issue , 2012, Pages 2589-2592

  Siniscalchi, Sabato Marco ^a,c   Li, Jinyu ^b   Lee, Chin Hui ^c  

^a KORE UNIVERSITY OF ENNA   (Italy)

^b MICROSOFT   (United States)

^c GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Adaptation algorithms; Connectionist speech recognition systems; Neural networks; Speech recognition

Indexed keywords

ADAPTATION ALGORITHMS; ADAPTATION PARAMETERS; ADAPTIVE CAPABILITIES; EXPERIMENTAL EVIDENCE; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; MULTI-LAYER PERCEPTRONS (MLPS); NEURAL ARCHITECTURES; SPEECH RECOGNITION SYSTEMS;

CONTINUOUS SPEECH RECOGNITION; NETWORK ARCHITECTURE; PATTERN RECOGNITION SYSTEMS; POLYNOMIALS; SPEECH RECOGNITION;

NEURAL NETWORKS;

EID: 84878606732     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. H. Bourlard and N. Morgan, Connectionist speech recognition - a hybrid approach. Norwell, MA, USA: Kluwer Academic Publisher, 1994.
2. J. S. Bridle, "Alpha-nets: a recurrent "neural" network architecture with a hidden Markov model interpretation," Speech Communication, vol. 9, no. 1, pp. 83-92, 1990.
3. A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural Networks, vol. 18, no. 5-6, pp. 602-610, 2005.
4. K. J. Lang, A. H. Waibel, and G. E. Hinton, "A time-delay neural network architecture for isolated word recognition," Neural Networks, vol. 3, pp. 23-43, 1990.
5. P. Schwarz, P. Matějka, and J. Černocky̌, "Hierarchical structures of neural networks for phoneme recognition," in Proc. ICASSP, (Toulouse, France), May 2006.
6. S. M. Siniscalchi, T. Svendsen, and C.-H. Lee, "Towards bottom-up continuous phone recognition," in Proc. ASRU, (Kyoto, Japan), pp. 556-569, Dec. 2007.
7. J. Pinto, B. Yegnanarayana, H. Hermansky, and M. Magimai-Doss, "Exploiting contextual information for improved phone recognition," in Proc. ICASSP, (Las Vegas, NV, USA), pp. 4449-4452, Mar./Apr. 2008.
8. G. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pre-trained deep neural networks for large vocabulary speech recognition," IEEE Trans. Audio, Speech and Language Processing, vol. 20, no. 1, pp. 30-42, 2012.
9. J. Neto, L. Almeida, M. Hochberg, C. Martins, L. Nunes, S. Renals, and T. Robinson, "Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system," in Proc. Eurospeech, (Madrid, Spain), pp. 2171-2174, Sept. 1995.
10. 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. 10-11, pp. 827-835, 2007.
11. S. M. Siniscalchi, T. Svendsen, S. Sorbello, and C.-H. Lee, "Experimental studies on continuous speech recognition using neural architectures with "adaptive" hidden activation functions," in Proc. ICASSP, (Dallas, TX, USA), pp. 4882-4885, Mar. 2010.
12. J. L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observation of Markov chains," IEEE Trans. on Speech and Audio Processing, vol. 2, no. 2, pp. 291-298, 1994.
13. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation for continuous density hidden Markov models," Computer Speech & Language, vol. 9, no. 2, pp. 171-185, 1995.
14. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in Proc. ASRU, (Hawaii, USA), pp. 24-29, Dec. 2011.
15. C. M. Bishop, Neural networks for pattern recognition. New York, USA: Oxford Univ. Press, 1995.
16. L. Ma and K. Khorasani, "Constructive feedforward neural networks using Hermite polynomial activation functions," IEEE Trans. Neural Networks, vol. 16, no. 4, pp. 821-833, 2005.
17. S. Gaglio, G. Pilato, F. Sorbello, and G. Vassallo, "Using the Hermite regression formula to design a neural architecture with automatic learning of the "hidden" activation functions," in Proc. of AI*IA, 1999.