Incremental Bayesian Adaptation
نویسنده
چکیده
Adaptive training is a powerful technique to build system on nonhomogeneous training data. A canonical model, representing “pure” speech variability and a set of transforms representing unwanted acoustic variabilities are trained. It is necessary to have transforms in order to deal with the testing acoustic conditions. One problem here is to robustly estimate the transforms parameters where there is limited or even no adaptation data. Recently, Lower bound based Bayesian approaches have been used to solve this problem in batch adaptation mode, of which point estimates, MAP or ML, and variational Bayes are two main approximation forms. This paper extends the Bayesian adaptation framework to incremental mode. Strict Bayesian inference and various approximated information propagation strategies during adaptation are discussed in detail. The techniques are examined for both ML and discriminative systems. The experiments on a large vocabulary speech recognition task showed that the incremental Bayesian adaptation can lead to robust performance with limited data at the start and gradually improve with more data available.
منابع مشابه
Behavior of a Bayesian adaptation method for incremental enrollment in speaker verification
متن کامل
Adapting Bayes Network Structures to Non-stationary Domains
When an incremental structural learning method gradually modifies a Bayesian network (BN) structure to fit a sequential stream of observations, we call the process structural adaptation. Structural adaptation is useful when the learner is set to work in an unknown environment, where a BN is gradually being constructed as observations of the environment are made. Existing algorithms for incremen...
متن کاملAdapting Bayes Network Structures to Non-stationary Domains — Technical Report
When an incremental structural learning method gradually modifies a Bayesian network (BN) structure to fit observations, as they are read from a database, we call the process structural adaptation. Structural adaptation is useful when the learner is set to work in an unknown environment, where a BN is to be gradually constructed as observations of the environment are made. Existing algorithms f...
متن کاملIncremental training of CDHMMs using bayesian learning
The Bayesian Learning approach (MAP Maximum A Posteriori) can be used for the incremental training of Continuous Density Hidden Markov Models (CDHMM), performed through speech data collected in real applications. The effectiveness of MAP is heavily conditioned by the correct balance between the a-priori knowledge and the field training data. In this paper we propose and evaluate several optimiz...
متن کاملBoosting long-term adaptation of hidden-Markov-models: incremental splitting of probability density functions
The research described in this paper focuses on possibilities to avoid the tedious training of Hidden-Markov-Models when setting up a new recognition task. A major speaker independent cause for the decrease of recognition accuracy is a mismatch of the phonetic contexts between training and testing data. To overcome this problem, we introduced in previous work the idea of an update of task indep...
متن کامل