Acoustic adaptation using nonlinear transformations of HMM parameters
نویسندگان
چکیده
Speech recognition performance degrades significantly when there is a mismatch between testing and training conditions. Linear transformation-based maximum-likelihood (ML) techniques have been proposed recently to tackle this problem. In this paper, we extend this approach to use nonlinear transformations. These are implemented by multilayer perceptrons (MLPs) which transform the Gaussian means. We derive a generalized expectationmaximization (GEM) training algorithm to estimate the MLP weights. Some preliminary experimental results on nonnative speaker adaptation are presented.
منابع مشابه
A unified framework of HMM adaptation with joint compensation of additive and convolutive distortions
In this paper, we present our recent development of a model-domain environment-robust adaptation algorithm, which demonstrates high performance in the standard Aurora 2 speech recognition task. The algorithm consists of two main steps. First, the noise and channel parameters are estimated using multi-sources of information including a nonlinear environment distortion model in the cepstral domai...
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-to-articulatory inversion using a speaker-normalized HMM-based speech production model
Acoustic-to-articulatory inverse mapping is a difficult problem because of its non-linear and oneto-many characteristics. We have previously developed a speech inversion method using a hidden Markov model (HMM)-based speech production model which takes into account the phonemespecific dynamic constraints of articulatory parameters. We found that the constraint significantly decreases the estima...
متن کاملBayesian affine transformation of HMM parameters for instantaneous and supervised adaptation in telephone speech recognition
This paper proposes a Bayesian affine transformation of hidden Markov model (HMM) parameters for reducing the acoustic mismatch problem in telephone speech recognition. Our purpose is to transform the existing HMM parameters into its new version of specific telephone environment using affine function so as to improve the recognition rate. The maximum a posteriori (MAP) estimation which merges t...
متن کاملFast adaptation of GMM-based compact models
In this paper, a new strategy for a fast adaptation of acoustic models is proposed for embedded speech recognition. It relies on a general GMM, which represents the whole acoustic space, associated with a set of HMM state-dependent probability functions modeled as transformations of this GMM. The work presented here takes advantage of this architecture to propose a fast and efficient way to ada...
متن کامل