Phoneme classification with multinets

The multinet phone classifier architecture is a framework for combining specialised phone detection networks into a posterior probability estimator for all phones. In this paper we give results obtained for the architecture on TIMIT phone classification tasks. We compare it with a standard mixture of Gaussian HMM classifiers.

[1]  Mike Schuster.  Acoustic model building based on non-uniform segments and bidirectional recurrent neural networks , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Michael Finke,et al.  ACID/HNN: clustering hierarchies of neural networks for context-dependent connectionist acoustic modeling , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[3]  Hervé Bourlard,et al.  Connectionist probability estimators in HMM speech recognition , 1994, IEEE Trans. Speech Audio Process..

[4]  Hsiao-Wuen Hon,et al.  Speaker-independent phone recognition using hidden Markov models , 1989, IEEE Trans. Acoust. Speech Signal Process..

[5]  Mohamed S. Kamel,et al.  Modular Neural Network Classifiers: A Comparative Study , 1998, J. Intell. Robotic Syst..

[6]  Kiyohiro Shikano,et al.  Modularity and scaling in large phonemic neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[7]  Kishan G. Mehrotra,et al.  Efficient classification for multiclass problems using modular neural networks , 1995, IEEE Trans. Neural Networks.

[8]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Michael I. Jordan,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1994, Neural Computation.

[10]  Anders Krogh,et al.  Neural Network Ensembles, Cross Validation, and Active Learning , 1994, NIPS.