Neural network acoustic model with decision tree clustered triphones

Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

Volumn , Issue , 2008, Pages 216-220

  Pavelka, Tomáš ^a   Král, Pavel ^a  

^a UNIVERSITY OF WEST BOHEMIA   (Czech Republic)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTICS; DECISION THEORY; DECISION TREES; HIDDEN MARKOV MODELS; LEARNING SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; ROBOT LEARNING; SIGNAL PROCESSING; SPEECH RECOGNITION; TECHNICAL PRESENTATIONS; TRELLIS CODES; VEGETATION; WIRELESS SENSOR NETWORKS;

ACOUSTIC MODELS; AUTOMATIC SPEECH RECOGNITIONS; EMISSION PROBABILITIES; GAUSSIAN MIXTURES; MULTI LAYERS; PHONETIC UNITS; SUPERIOR PERFORMANCES; TRAINING TIMES;

NEURAL NETWORKS;

EID: 58049151706     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/MLSP.2008.4685482     Document Type: Conference Paper

References (10)

1. Lawrence R. Rabiner, "A tutorial on hidden markov models and selected applications in speech recognition," in Proceedings ofthe IEEE, 1989.
2. Herve Bourlard and Nelson Morgan, "Hybrid HMM/ANN systems for speech recognition: Overview and new research directions," in Summer School on Neural Networks, 1997, pp. 389-417.
3. Joe Tebelskis, Speech Recognition using Neural Networks, Ph.D. thesis, Carnegie Mellon University, School of Computer Science, Pittsburgh, 1995.
4. Tomáš Pavelka and Kamil Ekštein, "Neural network acoustic model for recognition of Czech speech," in PhD Workshop Systems & Control, 2005.
5. Jan Hejtmánek and Tomáš Pavelka, "Use of context-dependent units in Czech speech," in PhD Workshop 2007, 2007.
6. Steve Young et al., The HTK Book (for HTK v. 3.3), Cambridge University Engineering Dept., 2002.
7. Julian Odell, The Use of Context in Large Vocabulary Speech Recognition, Ph.D. thesis, Cambridge University Engineering Department, 1995.
8. Michael Cohen, David Rummelhart, Nelson Morgan, Horacio Franco, Victor Abrash, and Yochai Konig, "Combining neural networks and hidden Markov models," in DARPA Speech and Natural Language Workshop, 1992.
9. Hervé Bourlard, Nelson Morgan, Chuck Wooters, and Steve Renals, "CDNN: a context dependent neural network for continuous speech recognition," in Acoustics, Speech, and Signal Processing ICASSP-92, 1992, vol. 2, pp. 349-352.
10. Tomáš Pavelka and Kamil Ekštein, "JLASER: An automatic speech recognizer written in Java," in XII International Conference Speech and Computer (SPECOM'2007), 2007.