MLLR مثبتي بر تبديل MAP تطبيق گوينده در بازشناسي گفتار پيوسته بر اساس تخمين

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

Several groups of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLR, where several general transforrnations are applied to model clusters, the results are desirable for small training data, but with increase in the amount of training data, the performance improvement saturates. In this paper, a new approach is introduced that makes use of the advantages of the both mentioned techniques to improve the recognition rate. Here, the models with available training data are trained using MAP while for those with insufficient training data, appropriate prior parameters for MAP estimation are found using MLLR. This technique has yielded better performance in comparison to either MAP or MLLR, in a system based on FARSDAT speech corpus.