Using broad phonetic group experts for improved speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 15, Issue 3, 2007, Pages 803-812

  Scanlon, Patricia ^a,b   Ellis, Daniel P W ^c   Reilly, Richard B ^a  

^a UNIVERSITY COLLEGE DUBLIN   (Ireland)

^b LUCENT TECHNOLOGIES   (United States)

^c Department of Earth and Environmental Sciences   (United States)

Author keywords

Automatic speech recognition; Broad phonetic groups (BPGs); Mixture of experts; Mutual information (MI)

Indexed keywords

ACOUSTIC MODELS; AUTOMATIC SPEECH RECOGNITION; BROAD PHONETIC GROUPS (BPGS); CONTEXT WINDOWS; CONTINUOUS SPEECH CORPORA; ERROR RATE REDUCTIONS; FEATURE SETS; INPUT FEATURES; MIXTURE OF EXPERTS; MUTUAL INFORMATION (MI); PHONE RECOGNITION; PHONEME RECOGNITION; PROPOSED ARCHITECTURES; SPECTRAL STRUCTURES; SPEECH RECOGNITION SYSTEMS; TEMPORAL CHARACTERISTICS; TIME FREQUENCIES;

CLASSIFIERS; FEATURE EXTRACTION; IMAGE CODING; LEARNING SYSTEMS; LINGUISTICS; SPEECH ANALYSIS; SPEECH PROCESSING; TELEPHONE SYSTEMS;

SPEECH RECOGNITION;

EID: 44849122716     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2006.885907     Document Type: Article

References (14)

1. J. Bilmes, "Maximum mutual information based reduction strategies for cross-correlation based joint distribution modelling," in Proc. Int. Conf. Acoust., Speech, Signal Process., Seattle, WA, 1998, pp. 469-472.
2. H. Bourlard and N. Morgan, Connectionist Speech Recognition: A Hybrid Approach. Norwell, MA: Kluwer, 1994.
3. S. Chang, S. Greenberg, and M. Wester, "An elitist approach to articulatory- acoustic feature classification," in Proc. Eurospeech, 2001, pp. 1725-1728.
4. T. M. Cover and J. A. Thomas, Elements of Information Theory. New York: Wiley, 1991.
5. A. Halberstadt and J. Glass, "Heterogeneous acoustic measurements for phonetic classification," in Proc. Eurospeech, 1997, pp. 401-404.
6. H. Hermansky, "Perceptual linear predictive (PLP) analysis for speech," J. Acoust. Soc. Amer., vol. 87, pp. 1738-1752, 1990.
7. A. Morris, J. Schwartz, and P. Escudier, "An information theoretical investigation into the distribution of phonetic information across the auditory spectrogram," Comput. Speech Lang., vol. 7, no. 2, pp. 121-136, 1993.
8. M. Rajamanohar and E. Fosler-Lussier, "An evaluation of hierarchical articulatory feature detectors," in IEEE Autom. Speech Recognition Understanding Workshop, 2005, pp. 59-64.
9. T. Reynolds and C. Antoniou, "Experiments in speech recognition using a modular mlp architecture for acoustic modelling," Inf. Sci., vol. 156, pp. 39-54, 2003.
10. P. Scanlon, D. P. W. Ellis, and R. Reilly, "Using mutual information to design class specific phone recognizers," in Proc. Eurospeech, 2003, pp. 857-860.
11. H. Schwenk, "Using boosting to improve a hybrid HMM/neural network speech recognizer," in Proc. Int. Conf. Acoust., Speech, Signal Process., 1999, pp. 1009-1012.
12. S. Sivadas and H. Hermansky, "Hierarchical tandem feature extraction," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2002, pp. 809-812.
13. H. Yang, S. V. Vuuren, S. Sharma, and H. Hermansky, "Relevance of time-frequency features for phonetic and speaker-channel classification," Speech Commun., vol. 31, pp. 35-50, 2000.
14. Y. Zhao, R. Schwartz, J. Sroka, and J. Makhoul, "Hierarchical mixtures of experts methodology applied to continuous speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process., 1995, pp. 3443-3446.