Speaker adaptation using probabilistic linear discriminant analysis for continuous speech recognition

The application of probabilistic linear discriminant analysis (PLDA) to speaker adaptation for automatic speech recognition based on hidden Markov models is proposed. By expressing the set of acoustic models of each of the training speakers in a matrix and treating each column as a sample, the small sample problem that can be encountered in PLDA if only one sample is available for each training speaker is overcome. In the continuous speech recognition experiments, the performance of the PLDA based approach improves over the principal component analysis (PCA) based approach and the two-dimensional PCA based approach for adaptation data longer than 12 s.