Recently, the Factorized Hidden Layer (FHL) adaptation is proposed for speaker adaptation of deep neural network (DNN) based acoustic models. In addition to the standard affine transformation, an FHL contains a speaker-dependent (SD) transformation matrix using a linear combination of rank-1 matrices and an SD bias using a linear combination of vectors. In this work, we extend the FHL based ada...

In this paper a novel speech feature generationbased acoustic model training method is proposed. For decades, speaker adaptation methods have been widely used. All existing adaptation methods need adaptation data. However, our proposed method creates speaker-independent acoustic models that cover not only known but also unknown speakers. We do this by adopting inverse maximum likelihood linear ...

This paper proposes a new voice conversion algorithm that modifies the source speaker’s speech to sound as if produced by a target speaker. To date, most approaches for speaker transformation are based on mapping functions or codebooks. We propose a linear filtering based approach to the problem of mapping the spectral parameters of one speaker to those of the other. In the proposed method, the...

In this paper, we present the study of the performance of our standard GMM speaker identi cation system in \a limited amount of training data" context. We explore the use of di erent mixture components for di erent speakers/models. Di erent approaches are presented: (a) a nonlinear transformation of speech duration vs. number of mixtures is proposed in order to set correctly the appropriate num...

The BBN BYBLOS continuous speech recognition system has been used to develop a method of speaker adaptation from limited training. The key step in the method is the estimation of a probabilistic spectral mapping between a prototype speaker, for whom there exists a well-trained speaker-dependent hidden Markov model (HMM), and a target speaker for whom there is only a small amount of training spe...

Speaker variability is one of the major error sources for ASR systems. Speaker adaptation estimates speaker specific models from the speaker independent ones to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. One of the commonly adopted approaches is the transformation based method. In this paper, the discriminative input and output transform...

This paper presents a new recursive Bayesian learning approach for transformation parameter estimation in speaker adaptation. Our goal is to incrementally transform (or adapt) the entire set of HMM parameters for a new speaker or new acoustic enviroment from a small amount of adaptation data. By establishing a clustering tree of HMM Gaus-sian mixture components, the nest aane transformation par...

Speaker adaptation is an important technique that can compensate for the mismatch between training data and the vocal characteristics of an individual user in a speech recognition system, however this can come at the cost of increased computational complexity. This paper reports a detailed comparison of four different affine transformation configurations for speaker adaptation, and the evaluati...

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 extend the well-known technique of constrained Maximum Likelihood Linear Regression (MLLR) to compute a projection (instead of a full rank transformation) on the feature vectors of the adaptation data. We model the projected features with phone-dependent Gaussian distributions and also model the complement of the projected space with a single class-independent, speaker-specific Gaussian dist...