Connectionist probability estimation in the DECIPHER speech recognition system

The authors have previously demonstrated that feedforward networks can be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems (Renals et al., 1991). These connectionist techniques are integrated into the DECIPHER system, with experiments being performed using the speaker-independent DARPA RM database. The results indicate that: connectionist probability estimation can improve performance of a context-independent maximum-likelihood-trained HMM system; performance of the connectionist system is close to what can be achieved using (context-dependent) HMM systems of much higher complexity; and mixing connectionist and maximum-likelihood estimates can improve the performance of the state-of-the-art context-independent HMM system.<<ETX>>

[1]  Lotfi A. Zadeh,et al.  Phonological structures for speech recognition , 1989 .

[2]  Mitch Weintraub,et al.  The decipher speech recognition system , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[3]  H. Gish,et al.  A probabilistic approach to the understanding and training of neural network classifiers , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[4]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Hynek Hermansky,et al.  Continuous speech recognition using PLP analysis with multilayer perceptrons , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[6]  Hervé Bourlard,et al.  Probability estimation by feed-forward networks in continuous speech recognition , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[7]  Jeff A. Bilmes,et al.  The Ring Array Processor: A Multiprocessing Peripheral for Connection Applications , 1992, J. Parallel Distributed Comput..