Maximum likelihood linear transformations for HMM-based speech recognition

Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabulary continuous speech recognition (LVCSR) systems are based on HMMs.

Whereas the basic principles underlying HMM-based LVCSR are rather straightforward, the approximations and simplifying assumptions involved in a direct implementation of these principles would result in a system which has poor accuracy and unacceptable sensitivity to changes in operating environment. Thus, the practical application of HMMs in modern systems involves considerable sophistication.

The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then describe the various refinements which are needed to achieve state-of-the-art performance. These refinements include feature projection, improved covariance modelling, discriminative parameter estimation, adaptation and normalisation, noise compensation and multi-pass system combination. The review concludes with a case study of LVCSR for Broadcast News and Conversation transcription in order to illustrate the techniques described.

/pdf/application-of-hidden-markov-models-in-speech-recognition-4ic3ad3d5g.pdf

Application of Hidden Markov Models in Speech Recognition

https://hal.archives-ouvertes.fr/hal-00499180/document

Automatic speech recognition and speech variability: A review

Deep Convolutional Neural Networks for Large-scale Speech Tasks

In an effort to reduce the degradation in speech recognition performance caused by variation in vocal tract shape among speakers, a frequency warping approach to speaker normalization is investigated. A set of low complexity, maximum likelihood based frequency warping procedures have been applied to speaker normalization for a telephone based connected digit recognition task. This paper presents an efficient means for estimating a linear frequency warping factor and a simple mechanism for implementing frequency warping by modifying the filter-bank in mel-frequency cepstrum feature analysis. An experimental study comparing these techniques to other well-known techniques for reducing variability is described. The results showed that frequency warping was consistently able to reduce word error rate by 20% even for very short utterances.

Speaker normalization using efficient frequency warping procedures

An experimental study describing the eeects of carbon and electret telephone transducers on automatic speech recognition (ASR) performance is presented. It is shown that telephone based ASR performance on a connected digit task actually improves when speech is spoken through the carbon transducer. This surprising result is explained by a study of the diierences in acoustic characteristics between carbon and electret telephone hand-sets. An initial attempt is made to devise a simple procedure for obtaining a parametric transformation which emulates the properties of the carbon transducer. The parameters of this transformation are trained automatically from speech spoken simultaneously through carbon and electret telephone handsets. When telephone speech data is transformed according to this procedure, a sig-niicant improvement in ASR performance is obtained. These results are interpreted and future research directions are discussed.

Li Lee

Papers

Speaker normalization using efficient frequency warping procedures

A feature-space transformation for telephone based speech recognition.