Download:
|
by Dongsuk Yuk, James Flanagan, Mahesh Krishnamoorthy, Krishna Dayanidhi
http://www.caip.rutgers.edu/~yuk/papers/eurospeech99.yuk.ps
Add To MetaCart
Abstract:
When there is a mismatch between training and testing conditions, statistical speech recognition algorithms suffer from severe degradation in recognition accuracy. The mismatch could be due to the interference from acoustical environments where systems are actually used or from speakers themselves. In this paper, a neural network based transformation approach is studied to handle the data distribution mismatches between training and testing conditions. The conditional probability that comes from hidden Markov model (HMM) based recognizers is used for the objective function of a neural network. It maximizes the likelihood of the data from a testing environment, and allows global optimization of the network when used with HMM-based recognizers. The new objective function can be used to transform speech feature vectors, or the mean vectors and covariance matrices of a recognizer. The proposed algorithm is evaluated on a noisy distant-talking version of the Resource Management database. 1.
Citations
|
2138
|
Learning Internal Representations by Error Propagation
– Rumelhart, Hinton, et al.
- 1986
|
|
800
|
Multilayer feedforward networks are universal approximators
– Hornik, Stinchcombe, et al.
- 1989
|
|
328
|
An introduction to computing with neural nets
– Lippmann
- 1987
|
|
72
|
A decision theoretic generalization of online learning and an application to boosting
– Freund, Schapire
- 1997
|
|
60
|
Global optimization of a neural network - hidden markov model hybrid
– Bengio, DeMori, et al.
- 1991
|
|
13
|
Noise reduction using connectionist models
– Tamura, Waibel
- 1988
|
|
11
|
Feature extraction based on minimum classi cation error/generalized probabilistic descent method
– Biem, Katagiri
- 1993
|
|
7
|
Simultaneous ANN feature and HMM recognizer design using string-based minimum classification error
– Rahim, Lee
- 1996
|
|
6
|
Telephone speech recognition using neural networks and hidden markov models
– Yuk, Flanagan
- 1999
|
|
5
|
Robust speech recognition using maximum likelihood neural networks and continuous density hidden Markov models
– Yuk, Che, et al.
- 1997
|
|
5
|
Environment-independent continuous speech recognition using neural networks and hidden Markov models
– Yuk, Che, et al.
- 1996
|
|
3
|
N-best breadth search for large vocabulary continuous speech recognition using a long span language model. 136th meeting of Acoustical Society of America
– Yuk, Che, et al.
- 1998
|
