Transformation and combination of hiden Markov models for speaker selection training

The Speaker Adaptation of an Acoustic Model

This paper deals with several adaptation techniques, which are of the importance in cases when the identity of a speaker is known and we want to recognize his speech. We are using three different methods, namely Maximum Apriori Probability adaptation, Maximum Likelihood Linear Regression and Constrained Maximum Likelihood Linear Regression. Each of the methods yields various benefits, therefore...

Transform ation and Com bination of Hidden M arkov M odels for Speaker Selection Training

This paper presents a 3-stage adaptation framework based on speaker selection training. First a subset of cohort speakers is selected for test speaker using Gaussian mixture model, which is more reliable given very limited adaptation data. Then cohort models are linearly transformed closer to each test speaker. Finally the adapted model for the test speaker is obtained by combining these transf...

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words

Temporal control and training selection for HMM-based system

Most speaker-independent acoustic-phonetic decoding systems are based on hidden Markov models. Such systems lack a real temporal control for the phonetic models. Furthermore, inter-speaker variability makes speaker adaptation necessary. In order to solve these problems, we introduce two original approaches. On the one hand, discontinuities detected with the ForwardBackward Divergence method are...