Linear transform adaptation techniques such as Maximum Likelihood Linear Regression (MLLR) are a popular and effective family of methods for speaker adaptation. MLLR estimates transform parameters for Gaussian means and variances using a maximum likelihood (ML) objective function. This paper discusses the use of an alternative discriminative objective function for linear transform estimation, w...

In this paper we describe a novel technique for adaptation of Gaussian means. The technique is related to Maximum Likelihood Linear Regression (MLLR), but we regress not on the mean itself but on a vector associated with each mean. These associated vectors are initialized by an ingenious technique based on eigen decomposition. As the only form of adaptation this technique outperforms MLLR, even...

However, it is generally difficult if not impossible to prepare a complete set of a priori noisy environment knowledge. Especially, the noisy environments which are not seen in the training phase (aka unseen noisy environment) may become potential sources of serious performance degradation for those non-blind methods. In other words, it is crucial how to well organize and efficiently utilize th...

Eigenspace-based MLLR (EMLLR) adaptation has been shown effective for fast speaker adaptation. It applies the basic idea of eigenvoice adaptation, and derives a small set of eigenmatrices using principal component analysis (PCA). The MLLR adaptation transformation of a new speaker is then a linear combination of the eigenmatrices. In this paper, we investigate the use of kernel PCA to find the ...

We discuss how to reduce the number of inverse matrix and its dimensions requested in MLLR framework for speaker adaptation. To find a smaller set of variables with less redundancy, we employ PCA(principal component analysis) and ICA(independent component analysis) that would give as good a representation as possible. The amount of additional computation when PCA or ICA is applied is as small a...

Connected strings of seven digits from the TIDIGITS database were recorded in a reverberant office room for evaluation using microphone array processing and HMM, Hidden Markov Model, adaptation. A sixteen-channel linear microphone array records a distance speech database useful for further experimentation. The adaptation techniques of Parallel Model Combination (PMC) and Maximum Likelihood Line...

When we want to develop a recognition system for a new environment, we have to decide which is the best option in what respect to the acoustic modeling: developing acoustic models from scratch using the data available for the new environment or to do cross-task adaptation starting from reliable HMM models. In this paper, we show the performance of several alternatives, comparing cross-task MAP ...

In this paper, we propose a novel speaker adaptation technique, regularized-MLLR, for Computer Assisted Language Learning (CALL) systems. This method uses a linear combination of a group of teachers’ transformation matrices to represent each target learner’s transformation matrix, thus avoids the over-adaptation problem that erroneous pronunciations come to be judged as good pronunciations afte...

Speaker adaptation techniques have emerged as very effective and practical methods to improve ASR performance on a test speaker with only limited speech data from the speaker. We explore the use of adaptation techniques on a new Voicemail database and present some theoretical extensions of the Cluster Transformation (CT) technique. Our experiments on 40 hours of voicemail data and four clusters...

In this paper, MLLR adaptation of continuous density HMM is investigated in a Farsi speaker independent large vocabulary continuous speech recognition system in attempt to improve recognition rate in real world situations. In the MLLR framework, we have experienced the use of Gaussian mean transformations in global adaptation and regression tree based adaptation. Besides full and block-diagonal...