On Adaptive Decision Rules and Decision Parameter Adaptation for Automatic Speech Recognition

Recent advances in automatic speech recognition are accomplished by designing a plug-in maximum a posteriori decision rule such that the forms of the acoustic and language model distributions are specified and the parameters of the assumed distributions are estimated from a collection of speech and language training corpora. Maximum likelihood point estimation is by far the most prevailing training method. However, due to the problems of unknown speech distributions, sparse training data, high spectral and temporal variabilities in speech, and possible mismatch between training and testing condition, a dynamic training stratedy is needed. To cope with the changing speakers and speaking conditions in real operational conditions for high performance speech recognition, such paradigms incorporate a small amount of speaker and environment specific adaptation data into the training process. Bayesian adaptive learning is an optimal way to combine prior knowledge in an existing collection of general models with a new set of condition-specific adaptation data. In this paper, the mathematical framwork for Bayesian adaptation of acoustic and language model parameters is first described. Maximum a posteriori point estimation is then developed for hidden Markov models and a number of useful parametric densities commonly used in automatic speech recognition and natural language processing. Other methods can be combined with Bayesian learning to enhance adaptation efficienty and effectiveness and therefore improve speech recognition performance. The same methodology and the set of Bayesian learning techniques can also be extended to other real-world pattern recognition problems.