Abstract not found

This dissertation describes a number of algorithms developed to increase the robustness of automatic speech recognition systems with respect to changes in the environment. These algorithms attempt to improve the recognition accuracy of speech recognition systems when they are trained and tested in different acoustical environments, and when a desk-top microphone (rather than a close-talking microphone) is used for speech input. Without such processing, mismatches between training and testing conditions produce an unacceptable degradation in recognition accuracy. Two kinds of

. In this paper, we discuss a new automatic speech recognition (ASR) approach based on independent processing and recombination of several feature streams. In this framework, it is assumed that the speech signal is represented in terms of multiple input streams, each input stream representing a different characteristic of the signal. If the streams are entirely synchronous, they may be accommodated simply (as they usually are in state-of-the-art systems). However, as discussed in the paper, it may be required to permit some degree of asynchrony between streams. This paper introduces the basic framework of a statistical structure that can accommodate multiple (asynchronous) observation streams (possibly exhibiting different frame rates). This approach will then be applied to the particular case of multi-band speech recognition and will be shown to yield significantly better noise robustness. 2 IDIAP--RR 96-07 1 Introduction In current automatic speech recognition (ASR) systems, the a...

In the framework of hidden Markov models (HMM) or hybrid HMM/Artificial Neural Network (ANN) systems, we present a new approach towards automatic speech recognition (ASR). The general idea is to split the whole frequency band (represented in terms of critical bands) into a few sub-bands on which different recognizers are independently applied and then recombined at a certain speech unit level to yield global scores and a global recognition decision. The preliminary results presented in this paper show that such an approach, even using quite simple recombination strategies, can yield at least comparable performance on clean speech while providing better robustness in the case of noisy speech.

is granted. A Maximum-Likelihood Approach to Stochastic Matching for Robust Speech Recognition Ananth Sankar 2 and Chin-Hui Lee Speech Research Department AT&T Bell Laboratories Murray Hill, NJ 07974 1 Introduction Recently there has been much interest in the problem of improving the performance of automatic speech recognition (ASR) systems in adverse environments. When there is a mismatch between the training and testing environments, ASR systems suffer a degradation in performance. The goal of robust speech recognition is to remove the effect of this mismatch so as to bring the recognition performance as close as possible to the matched conditions. In speech recognition, the speech is usually modeled by a set of hidden Markov models (HMM) X . During recognition the observed utterance Y is decoded using these models. Due to the mismatch between training and testing conditions, this often results in a degradation in performance compared to the matched conditions. The mismatch b...

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 specific data, and are often based on initial speaker independent (SI) recognition systems. Some of these speaker adaptation techniques may also be applied to the task of adaptation to a new acoustic environment. In this case a SI recognition system trained in, typically, a clean acoustic environment is adapted to operate in a new, noise-corrupted, acoustic environment. This paper examines the Maximum Likelihood Linear Regression (MLLR) adaptation technique. MLLR estimates linear transformations for groups of models parameters to maximise the likelihood of the adaptation data. Previously, MLLR has been applied to the mean parameters in mixture Gaussian HMM systems. In this paper MLLR is extended to also update the Gaussian variances and re-estimation formulae are derived for these variance transforms. MLLR with variance compensation is evaluated on several large vocabulary recognition tasks. The use of mean and variance MLLR adaptation was found to give an additional 2% to 7% decrease in word error rate over mean-only MLLR adaptation. 1

This paper addresses the problem of automatic speech recognition in the presence of interfering noise. It focuses on the Parallel Model Combination (PMC) scheme, which has been shown to be a powerful technique for achieving noise robustness. Most experiments reported on PMC to date have been on small, 10-50 word vocabulary systems. Experiments on the Resource Management (RM) database, a 1000 word continuous speech recognition task, reveal compensation requirements not highlighted by the smaller vocabulary tasks. In particular, that it is necessary to compensate the dynamic parameters as well as the static parameters to achieve good recognition performance. The database used for these experiments was the RM speaker independent task with either Lynx Helicopter noise or Operation Room noise from the NOISEX-92 database added. The experiments reported here used the HTK RM recogniser developed at CUED modified to include PMC based compensation for the static, delta and delta-delta parameters. After training on clean speech data,the performance of the recogniser was found to be severely degraded when noise was added to the speech signal at between 10dB and 18dB. However, using PMC the performance was restored to a level comparable with that obtained when training directly in the noise corrupted environment. 1

Source separation, or computational auditory scene analysis, attempts to extract individual acoustic objects from input which contains a mixture of sounds from different sources, altered by the acoustic environment. Unmixing algorithms such as ICA and its extensions recover sources by reweighting multiple observation sequences, and thus cannot operate when only a single observation signal is available. I present a technique called refiltering which recovers sources by a nonstationary reweighting ("masking") of frequency sub-bands from a single recording, and argue for the application of statistical algorithms to learning this masking function. I present results of a simple factorial HMM system which learns on recordings of single speakers and can then separate mixtures using only one observation signal by computing the masking function and then refiltering.

Visual speech information from the speaker’s mouth region has been successfully shown to improve noise robustness of automatic speech recognizers, thus promising to extend their usability in the human computer interface. In this paper, we review the main components of audio-visual automatic speech recognition and present novel contributions in two main areas: First, the visual front end design, based on a cascade of linear image transforms of an appropriate video region-of-interest, and subsequently, audio-visual speech integration. On the latter topic, we discuss new work on feature and decision fusion combination, the modeling of audio-visual speech asynchrony, and incorporating modality reliability estimates to the bimodal recognition process. We also briefly touch upon the issue of audio-visual adaptation. We apply our algorithms to three multi-subject bimodal databases, ranging from small- to large-vocabulary recognition tasks, recorded in both visually controlled and challenging environments. Our experiments demonstrate that the visual modality improves automatic speech recognition over all conditions and data considered, though less so for visually challenging environments and large vocabulary tasks.

Maximum likelihood linear regression (MLLR) is an adaptation technique suitable for both speaker and environmental model-based adaptation. The models are adapted using a set of linear transformations, estimated in a maximum likelihood fashion from the available adaptation data. As these transformations can capture general relationships between the original model set and the current speaker, or new acoustic environment, they can be effective in adapting all the HMM distributions with limited adaptation data. Two important decisions that must be made are (i) how to cluster components together, such that they all have a similar transformation matrix, and (ii) how many transformation matrices to generate for a given block of adaptation data. This paper addresses both problems. Firstly it describes two optimal clustering techniques, in the sense of maximising the likelihood of the adaptation data. The first assigns each component to one of the regression classes. This may be used to generat...