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

Abstract-This paper presents a person identification system based on acoustic and visual features. The system is organized as a set of non-homogeneous classifiers whose outputs are integrated after a normalization step. In particular, two classifiers based on acoustic features and three based on visual ones provide data for an integration module whose performance is evaluated. A novel technique for the integration of multiple classifiers at an hybrid ranWmeasurement level is introduced using HyperBF networks. Two different methods for the rejection of an unknown person are introduced. The performance of the integrated system is shown to be superior to that of the acoustic and visual subsystems. The resulting identification system can be used to log personal access and, with minor modifications, as an identity verification system. Index Tenns-Template matching, robust statistics, correlation, face recognition, speaker recognition, learning, classification. I.

A tutorial on the design and development of automatic speaker-recognition systems is presented. Automatic speaker recognition is the use of a machine to recognize a person from a spoken phrase. These systems can operate in two modes: to identify a particular person or to verify a person’s claimed identity. Speech processing and the basic components of automatic speakerrecognition systems are shown and design tradeoffs are discussed. Then, a new automatic speaker-recognition system is given. This recognizer performs with 98.9 % correct identification. Last, the performances of various systems are compared.

decide which contexts are similar and can share parameters. A key feature of this approach is that it allows the construction of models which are dependent upon contextual effects occurring across word boundaries. The use of cross word context dependent models presents problems for conventional decoders. The second part of the thesis therefore presents a new decoder design which is capable of using these models efficiently. The decoder is suitable for use with very large vocabularies and long span language models. It is also capable of generating a lattice of word hypotheses with little computational overhead. These lattices can be used to constrain further decoding, allowing efficient use of complex acoustic and language models. The effectiveness of these techniques has been assessed on a variety of large vocabulary continuous speech recognition tasks and results are presented which analyse performance in terms of computational complexity and recognition accuracy. The experiments dem

We propose a novel feature mapping approach that is robust to channel mismatch, additive noise and to some extent, nonlinear effects attributed to handset transducers. These adverse effects can distort the short-term distribution of the speech features. Some methods have addressed this issue by conditioning the variance of the distribution, but not to the extent of conforming the speech statistics to a target distribution. The proposed target mapping method warps the distribution of a cepstral feature stream to a standardised distribution over a specified time interval. We evaluate a number of the enhancement methods for speaker verification, and compare them against a Gaussian target mapping implementation. Results indicate improvements of the warping technique over a number of methods such as Cepstral Mean Subtraction (CMS), modulation spectrum processing, and short-term windowed CMS and variance normalisation. This technique is a suitable feature post-processing method that may be combined with other techniques to enhance speaker recognition robustness under adverse conditions.

Graphical models provide a promising paradigm to study both existing and novel techniques for automatic speech recognition. This paper first provides a brief overview of graphical models and their uses as statistical models. It is then shown that the statistical assumptions behind many pattern recognition techniques commonly used as part of a speech recognition system can be described by a graph – this includes Gaussian distributions, mixture models, decision trees, factor analysis, principle component analysis, linear discriminant analysis, and hidden Markov models. Moreover, this paper shows that many advanced models for speech recognition and language processing can also be simply described by a graph, including many at the acoustic-, pronunciation-, and language-modeling levels. A number of speech recognition techniques born directly out of the graphical-models paradigm are also surveyed. Additionally, this paper includes a novel graphical analysis regarding why derivative (or delta) features improve hidden Markov model-based speech recognition by improving structural discriminability. It also includes an example where a graph can be used to represent language model smoothing constraints. As will be seen, the space of models describable by a graph is quite large. A thorough exploration of this space should yield techniques that ultimately will supersede the hidden Markov model.

Contents 1 Spoken Language Input 1 Ron Cole & Victor Zue, chapter editors 1.1 Overview : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 1 Victor Zue & Ron Cole 1.2 Speech Recognition : : : : : : : : : : : : : : : : : : : : : : : : : : : 4 Victor Zue, Ron Cole, & Wayne Ward 1.3 Signal Representation : : : : : : : : : : : : : : : : : : : : : : : : : : 11 Melvyn J. Hunt 1.4 Robust Speech Recognition : : : : : : : : : : : : : : : : : : : : : : 17 Richard M. Stern 1.5 HMM Methods in Speech Recognition : : : : : : : : : : : : : : : 24 Renato De Mori & Fabio Brugnara 1.6 Language Representation : : : : : : : : : : : : : : : : : : : : : : : : 35 Salim Roukos 1.7 Speaker Recognition : : : : : : : : : : : : : : : : : : : : : : : : : : :<F35.37

Statistical techniques based on hidden Markov Models (HMMs) with Gaussian emission densities have dominated signal processing and pattern recognition literature for the past 20 years. However, HMMs trained using maximum likelihood techniques suffer from an inability to learn discriminative information and are prone to overfitting and over-parameterization. Recent work in machine learning has focused on models, such as the support vector machine (SVM), that automatically control generalization and parameterization as part of the overall optimization process. In this paper, we show that SVMs provide a significant improvement in performance on a static pattern classification task based on the Deterding vowel data. We also describe an application of SVMs to large vocabulary speech recognition, and demonstrate an improvement in error rate on a continuous alphadigit task (OGI Aphadigits) and a large vocabulary conversational speech task (Switchboard). Issues related to the development and optimization of an SVM/HMM hybrid system are discussed.

The paper discusses author’s experience with applying auditory knowledge to automatic recognition of speech. It indirectly argues against blind implementing of scattered accidental knowledge which may be irrelevant to a speech recognition task. It advances the notion that the reason for applying knowledge of human auditory perception in engineering applications should be the ability of perception to suppress some parts of information in the speech message. Three properties of human speech perception: limited spectral resolution, use of information from about syllable-length segments ability to alleviate unreliable cues, are discussed in some detail. Overall, we are advocating selective use of auditory knowledge,optimized on real speechdata. Fig. I A good hard working man. Fig. II A foolish man?

This paper gives an overview of automatic speaker recognition technology, with an emphasis on text-independent recognition. Speaker recognition has been studied actively for several decades. We give an overview of both the classical and the state-of-the-art methods. We start with the fundamentals of automatic speaker recognition, concerning feature extraction and speaker modeling. We elaborate advanced computational techniques to address robustness and session variability. The recent progress from vectors towards supervectors opens up a new area of exploration and represents a technology trend. We also provide an overview of this recent development and discuss the evaluation methodology of speaker recognition systems. We conclude the paper with discussion on future directions.