Variance compensation within the MLLR framework for robust speech recognition and speaker adaptation
نویسندگان
چکیده
This paper investigates the use of maximum likelihood linear regression (MLLR) for both speaker and environment adaptation. MLLR transforms the mean and variance parameters of a set of HMMs. In this paper a number of different types of linear transformations of the variances are examined including full, block diagonal, and diagonal transformation matrices. Experiments on large vocabulary speaker independent data sets are described. On all the data sets examined the use of MLLR mean and variance compensation reduced the error rate compared to mean-only compensation. Furthermore, the use of a block diagonal or full transformation of the variances on the clean data task showed slight improvements over the diagonal case. However, when some environmental mismatch was present there was no difference in performance between using multiple diagonal variance transformations and a more complex single variance transform.
منابع مشابه
Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety 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 MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety 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 MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملMean and variance adaptation within the MLLR framework
One of the key issues for adaptation algorithms is to modify a large number of parameters with only a small amount of adaptation data. Speaker adaptation techniques try to obtain near speaker dependent (SD) performance with only small amounts of speaker speciic data, and are often based on initial speaker independent (SI) recognition systems. Some of these speaker adaptation techniques may also...
متن کاملAcoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition
A novel speech feature generation-based acoustic model training method for robust speaker-independent speech recognition is proposed. For decades, speaker adaptation methods have been widely used. All of these adaptation methods need adaptation data. However, our proposed method aims to create speaker-independent acoustic models that cover not only known but also unknown speakers. We achieve th...
متن کاملRobust Speech Recognition Usin Intra-speaker Ada
Inter-speaker variation can be coped rather well in speech recognition by speaker adaptation techniques such as MLLR and MAP. However, when dealing with speech other than reading style, such as conversational speech, emotional speech and so on, current recognition systems cannot achieve a satisfactory performance even after speaker adaptation. In view of this situation, two-level adaptation met...
متن کامل