A MAP-like weighting scheme for MLLR speaker adaptation
نویسندگان
چکیده
This paper presents an approach for fast, unsupervised, online MLLR speaker adaptation using two MAP-like weighting schemes, a static and a dynamic one. While for the standard MLLR approach several sentences are necessary before a reliable estimation of the transformations is possible, the weighted approach shows good results even if adaptation is conducted after only a few short utterances. Experimental results show that using the static approach can improve the word error rate by approx. 27% if adaptation is conducted after every 4 utterances (single words or short phrases). Using the dynamic approach, results can be improved by 28%. The most important advantage of the dynamic weight is that it is rather insensitive with respect to the initial weight whereas for the static approach it is very critical which initial weight to chose. Moreover, useful values for the weights in the static case depend very much on the corpus. If the standard MLLR approach is used, even a drastic increase in sentence error rate can be observed for these small amounts of adaptation data.
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 کاملA Combined MAP + MLLR Approach for Speaker Adaptation
A new approach for speaker adaptation consisting of MLLR adaptation enriched by a special weighting scheme followed by MAP adaptation is presented. While the standard MLLR approach increases the error rate for the considered small amounts of adaptation data in on-line, unsupervised adaptation, our approach can reduce the error by up to 30%. This result can further be improved by switching to MA...
متن کاملUnsupervised Speaker Adaptation Using Reference Speaker Weighting
Recently, we revisited the fast adaptation method called reference speaker weighting (RSW), and suggested a few modifications. We then showed that the algorithmically simplest technique actually outperformed conventional adaptation techniques like MAP and MLLR for 5or 10-second supervised adaptation on the Wall Street Journal 5K task. In this paper, we would like to further investigate the perf...
متن کاملRobustness of several kernel-based fast adaptation methods on noisy LVCSR
We have been investigating the use of kernel methods to improve conventional linear adaptation algorithms for fast adaptation, when there are less than 10s of adaptation speech. On clean speech, we had shown that our new kernel-based adaptation methods, namely, embedded kernel eigenvoice (eKEV) and kernel eigenspace-based MLLR (KEMLLR) outperformed their linear counterparts. In this paper, we s...
متن کامل