A hierarchical, context-dependent neural network architecture for improved phone recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2011, Pages 5040-5043

  Tóth, László ^a  

^a UNIVERSITY OF SZEGED   (Hungary)

Author keywords

bottleneck; HMM ANN; MLP; Phone recognition; TIMIT

Indexed keywords

BOTTLENECK; HMM/ANN; MLP; PHONE RECOGNITION; TIMIT;

NETWORK ARCHITECTURE; NEURAL NETWORKS; SIGNAL PROCESSING; SPEECH COMMUNICATION; SPEECH RECOGNITION; TELEPHONE SETS;

TELEPHONE CIRCUITS;

EID: 80051620271     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947489     Document Type: Conference Paper

References (15)

1. H. Bourlard and N. Morgan, Connectionist Speech Recognition - A Hybrid Approach, Kluwer, 1994.
2. H. Hermansky, D. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in ICASSP, 2000, pp. 1635-1638.
3. P. Schwarz, P. Matějka, and J. Černocký, "Hierarchical structures of neural networks for phoneme recognition," in ICASSP, 2006, pp. 325-328.
4. H. Ketabdar and H. Bourlard, "Enhanced phone posteriors for improving speech recognition systems," IEEE Trans. ASLP, vol. 18, no. 6, pp. 1094-1106, 2010.
5. J. Pinto et al., "Analysis of MLP based hierarchical phoneme posterior probability estimator," IEEE Trans. ASLP, vol. in press, 2010.
6. S. Young et al., The HTK Book, Cambridge University Engineering Department, 2005.
7. H. Bourlard, N. Morgan, C. Wooters, and S. Renals, "CDNN: A context dependent neural network for continuous speech recognition," in ICASSP, 1992, vol. II, pp. 349-353.
8. T. Pavelka and P. Král, "Neural network acoustic model with decision tree clustered triphones," in MLSP, 2008, pp. 216-220.
9. A. Abad, T. Pellegrini, I. Trancoso, and J. Neto, "Context dependent modelling approaches for hybrid speech recognizers," in Interspeech, 2010.
10. F. Grézl,M. Karafiát, S. Kontár, and J. Černocký, "Probabilistic and bottle-neck features for LVCSR of meetings," in ICASSP, 2007, pp. 757-760.
11. A.-R. Mohamed, G. Dahl, and G. Hinton, "Deep belief networks for phone recognition," in NIPS 22 workshop on deep learning for speech recognition, 2009.
12. S.-Y. Chang and L.-S. Lee, "Improved clustered hierarchical tandem system with bottom-up processing," in ICASSP, 2009, pp. 4441-4444.
13. J. Frankel, D. Wang, and S. King, "Growing bottleneck features for tandem ASR," in Interspeech, 2008, p. 1549.
14. Y. Hifny and S. Renals, "Speech recognition using conditional random fields," IEEE Trans. ASLP, vol. 17, no. 2, pp. 354-365, 2009.
15. S.-M. Siniscalchi, P. Schwarz, and C.-H. Lee, "High-accuracy phone recognition by combining high performance lattice generation and knowledge based rescoring," in ICASSP, 2007, pp. 869-872.