Speaker adaptation using combined transformation and Bayesian methods
V Digalakis, L Neumeyer - 1995 International Conference on …, 1995 - ieeexplore.ieee.org
The performance and robustness of a speech recognition system can be improved by
adapting the speech models to the speaker, the channel and the task. In continuous mixture …
adapting the speech models to the speaker, the channel and the task. In continuous mixture …
Speaker adaptation using combined transformation and Bayesian methods
VV Digalakis, LG Neumeyer - IEEE transactions on speech and …, 1996 - ieeexplore.ieee.org
Adapting the parameters of a statistical speaker independent continuous-speech recognizer
to the speaker and the channel can significantly improve the recognition performance and …
to the speaker and the channel can significantly improve the recognition performance and …
Speaker adaptation using constrained estimation of Gaussian mixtures
VV Digalakis, D Rtischev… - IEEE Transactions on …, 1995 - ieeexplore.ieee.org
A trend in automatic speech recognition systems is the use of continuous mixture-density
hidden Markov models (HMMs). Despite the good recognition performance that these …
hidden Markov models (HMMs). Despite the good recognition performance that these …
Improved Bayesian learning of hidden Markov models for speaker adaptation
We propose an improved maximum a posteriori (MAP) learning algorithm of continuous-
density hidden Markov model (CDHMM) parameters for speaker adaptation. The algorithm …
density hidden Markov model (CDHMM) parameters for speaker adaptation. The algorithm …
[PDF][PDF] A comparative study of speaker adaptation techniques
L Neumeyer, A Sankar, V Digalakis - system, 1995 - researchgate.net
In previous work, we showed how to constrain the estimation of continuous mixture-density
hidden Markov models (HMMs) when the amount of adaptation data is small. We used …
hidden Markov models (HMMs) when the amount of adaptation data is small. We used …
Speaker adaptation for large vocabulary speech recognition systems using speaker Markov models
G Rigoll - International Conference on Acoustics, Speech, and …, 1989 - ieeexplore.ieee.org
An alternative approach to speaker adaptation for a large-vocabulary hidden-Markov-model-
based speech recognition system is described. The goal of this investigation was to train the …
based speech recognition system is described. The goal of this investigation was to train the …
Speaker adaptation with autonomous model complexity control by MDL principle
K Shinoda, T Watanabe - 1996 IEEE International Conference …, 1996 - ieeexplore.ieee.org
A speaker adaptation method for continuous density HMMs, which performs well for any
amount of data for adaptation, is proposed. This method estimates shift parameters for the …
amount of data for adaptation, is proposed. This method estimates shift parameters for the …
Structural MAP speaker adaptation using hierarchical priors
Most adaptation methods for speech recognition using hidden Markov models fall into two
categories; one is the Bayesian approach, where prior distributions for the model …
categories; one is the Bayesian approach, where prior distributions for the model …
Speaker adaptation based on MAP estimation of HMM parameters
CH Lee, JL Gauvain - 1993 IEEE International Conference on …, 1993 - ieeexplore.ieee.org
A number of issues related to the application of Bayesian learning techniques to speaker
adaptation are investigated. It is shown that the seed models required to construct prior …
adaptation are investigated. It is shown that the seed models required to construct prior …
N-best-based instantaneous speaker adaptation method for speech recognition
An instantaneous speaker adaptation method is proposed that uses N-best decoding for
continuous mixture-density hidden Markov model-based speech recognition systems. An N …
continuous mixture-density hidden Markov model-based speech recognition systems. An N …