Unsupervised speaker adaptation using high confidence portion recognition results by multiple recognition systems
نویسندگان
چکیده
This paper describes an accurate unsupervised speaker adaptation method for lecture speech recognition using multiple LVCSRs. In an unsupervised speaker adaptation framework, the improvement of recognition performance by adapting acoustic models greatly depends on the accuracy of labels such as phonemes and syllables. Therefore, extraction of the adaptation data guided by the confidence measures is effective for unsupervised adaptation. In this paper, we looked for the high confidence portions based on the agreement between two LVCSRs, adapted acoustic models using the portions attached with high accurate labels, and then improved the recognition accuracy. We applied our method to the Corpus of Spontaneous Japanese (CSJ) and the method improved the recognition rate by about 5% in comparison with a traditional method.
منابع مشابه
An Unsupervised Speaker Adaptation Method for Lecture-Style Spontaneous Speech Recognition Using Multiple Recognition Systems
This paper describes an accurate unsupervised speaker adaptation method for lecture style spontaneous speech recognition using multiple LVCSR systems. In an unsupervised speaker adaptation framework, the improvement of recognition performance by adapting acoustic models remarkably depends on the accuracy of labels such as phonemes and syllables. Therefore, extraction of the adaptation data guid...
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 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 کاملSemi-supervised speaker adaptation
We developed powerful unsupervised adaptation methods for speech recognition, i.e., the system improves its performance while the user uses it. No prior enrollment phase is necessary where the speaker has to read a given text. We tried to further improve the unsupervised adaptation by using confidence measures. These give an estimate of how likely the recognized words were correct. Adaptation t...
متن کاملImproved MLLR speaker adaptation using confidence measures for conversational speech recognition
Automatic recognition of conversational speech tends to have higher word error rates (WER) than read speech. Improvements gained from unsupervised speaker adaptation methods like Maximum Likelihood Linear Regression (MLLR) [1] are reduced because of their sensitivity to recognition errors in the first pass. We show that a more detailed modeling of adaptation classes and the use of confidence me...
متن کامل