Text-independent Speaker Identification Research Articles

Codebook design using genetic algorithm and its application to speaker identification

A new codebook design algorithm for text-independent speaker identification based on the discrete hidden Markov model (HMM) is proposed. The optimisation criterion of the new training procedure is to make each codevector in the codebook to represent the same number of training vectors approximately rather than to minimise the quantisation error. This idea is implemented with a genetic algorithm. The new codebook is evaluated experimentally. It is shown that, for a small codebook, the speaker identification performance using the new codebook is better than that obtained using the Linde-Buzo-Grey codebook for HMM-based speaker identification.

A Model-Selection-Based Self-Splitting Gaussian Mixture Learning with Application to Speaker Identification

We propose a self-splitting Gaussian mixture learning (SGML) algorithm for Gaussian mixture modelling. The SGML algorithm is deterministic and is able to find an appropriate number of components of the Gaussian mixture model (GMM) based on a self-splitting validity measure, Bayesian information criterion (BIC). It starts with a single component in the feature space and splits adaptively during the learning process until the most appropriate number of components is found. The SGML algorithm also performs well in learning the GMM with a given component number. In our experiments on clustering of a synthetic data set and the text-independent speaker identification task, we have observed the ability of the SGML for model-based clustering and automatically determining the model complexity of the speaker GMMs for speaker identification.

Pitch Correlogram Clustering for Fast Speaker Identification

Gaussian mixture models (GMMs) are commonly used in text-independent speaker identification systems. However, for large speaker databases, their high computational run-time limits their use in online or real-time speaker identification situations. Two-stage identification systems, in which the database is partitioned into clusters based on some proximity criteria and only a single-cluster GMM is run in every test, have been suggested in literature to speed up the identification process. However, most clustering algorithms used have shown limited success, apparently because the clustering and GMM feature spaces used are derived from similar speech characteristics. This paper presents a new clustering approach based on the concept of a pitch correlogram that captures frame-to-frame pitch variations of a speaker rather than short-time spectral characteristics like cepstral coefficient, spectral slopes, and so forth. The effectiveness of this two-stage identification process is demonstrated on the IVIE corpus of 110 speakers. The overall system achieves a run-time advantage of 500% as well as a 10% reduction of error in overall speaker identification.

On the Determination of Optimal Model Order for GMM-Based Text-Independent Speaker Identification

Gaussian mixture models (GMMs) are recently employed to provide a robust technique for speaker identification. The determination of the appropriate number of Gaussian components in amodel for adequate speaker representation is a crucial but difficult problem. This number is in fact speaker dependent. Therefore, assuming a fixed number of Gaussian components for all speakers is not justified. In this paper, we develop a procedure for roughly estimating the maximum possible model order above which the estimation of model parameters becomes unreliable. In addition, a theoretical measure, namely, a goodness of fit (GOF) measure is derived and utilized in estimating the number of Gaussian components needed to characterize different speakers. The estimation is carried out by exploiting the distribution of the training data for each speaker. Experimental results indicate that the proposed technique provides results comparable to other well-known model selection criteria like the minimum description length (MDL) and the Akaike information criterion (AIC).

Speaker identification using hybrid Karhunen–Loeve transform and Gaussian mixture model approach

This paper proposes a classification scheme that incorporates Karhunen–Loeve transform (KLT) and Gaussian mixture model (GMM) for text-independent speaker identification. Our results show that the combination is beneficial to both classification accuracy and computational cost. For a database with 500 Mandarin speakers, it is demonstrated that accuracy improvement of up to 4% and computational cost saving of 10 times compared to those of the conventional GMM model can be achieved.

Speaker identification by combining multiple classifiers using Dempster–Shafer theory of evidence

This paper presents a multiple classifier approach as an alternative solution to the closed-set text-independent speaker identification problem. The proposed algorithm which is based on Dempster–Shafer theory of evidence computes the first and Rth level ranking statistics. Rth level confusion matrices extracted from these ranking statistics are used to cluster the speakers into model sets where they share set specific properties. Some of these model sets are used to reflect the strengths and weaknesses of the classifiers while some others carry speaker dependent ranking statistics of the corresponding classifier. These information sets from multiple classifiers are combined to arrive at a joint decision. For the combination task, a rule-based algorithm is developed where Dempster’s rule of combination is applied in the final step. Experimental results have shown that the proposed method performed much better compared to some other rank-based combination methods.

Application of time-frequency principal component analysis to text-independent speaker identification

We propose a formalism, called vector filtering of spectral trajectories, that allows the integration of a number of speech parameterization approaches (cepstral analysis, /spl Delta/ and /spl Delta//spl Delta/ parameterizations, auto-regressive vector modeling, ...) under a common formalism. We then propose a new filtering, called contextual principal components (CPC) or time-frequency principal components (TFPC). This filtering consists in extracting the principal components of the contextual covariance matrix, which is the covariance matrix of a sequence of vectors expanded by their context. We apply this new filtering in the framework of closed-set speaker identification, using a subset of the POLYCOST database. When using speaker-dependent TFPC filters, our results show a relative improvement of approximately 20% compared to the use of the classical cepstral coefficients augmented by their /spl Delta/-coefficients, which is significantly better with a 90% confidence level.

Forensic speaker identification based on spectral moments

A new method for doing text-independent speaker identification geared to forensic situations is presented. By analysing ‘isolexemic’ sequences, the method addresses the issues of very short criminal exemplars and the need for open-set identification. An algorithm is given that computes an average spectral shape of the speech to be analysed for each glottal pulse period. Each such spectrum is converted to a probability density function and the first moment (i.e. the mean) and the second moment about the mean (i.e. the variance) are computed. Sequences of moment values are used as the basis for extracting variables that discriminate among speakers. Ten variables are presented all of which have sufficiently high inter- to intraspeaker variation to be effective discriminators. A case study comprising a ten-speaker database, and ten unknown speakers, is presented. A discriminant analysis is performed and the statistical measurements that result suggest that the method is potentially effective. The report represents work in progress.

Neural networks for improved text-independent speaker identification.

In this article, we consider the binary partitioned approach with pattern index information, propose an neural network array (NNA) that performs the pattern recognition task by combining the binary partitioned approach with decision trees, and verify that the NNA can not only reduce the computation cost of training and recognition but also reduce the classification error rate. Speaker identification with the radial basis function neural network array (RBFNNA) is discussed in detail as an application of the NNA.

Robust speech features based on wavelet transform with application to speaker identification

An effective and robust speech feature extraction method is presented. Based on the time–frequency multiresolution property of wavelet transform, the input speech signal is decomposed into various frequency channels. For capturing the characteristics of an individual speaker, the linear predictive cepstral coefficients of the approximation channel and entropy value of the detail channel for each decomposition process are calculated. In addition, an adaptive thresholding technique for each lower resolution is also applied to remove the influence of noise interference. Experimental results show that using this mechanism not only effectively reduces the influence of noise interference but also improves the recognition performance. Finally, the proposed method is evaluated on the MAT telephone speech database for text-independent speaker identification using the group vector quantisation identifier. Some popular existing methods are also evaluated for comparison, and the results show that the proposed feature extraction algorithm is more effective and robust than the other existing methods. In addition, the performance of the proposed method is very satisfactory even in a low SNR environment corrupted by Gaussian white noise.

Text-independent speaker identification based on explicit exploitation of stochastic characteristics of test utterance

The benefit of exploiting the stochastic characteristics of test utterance for speaker identification (speaker ID) via cross likelihood ratio and Bayesian information criterion is explored. Simulation results demonstrate the superiority of the proposed approaches over the conventional speaker ID based on maximum likelihood decision rule.

Apparatus and methods for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases

A method and apparatus for securing access to a service or facility employing automatic speech recognition, text-independent speaker identification, natural language understanding techniques and additional dynamic and static features. The method includes the steps of receiving and decoding speech containing indicia of the speaker such as a name, address or customer number; accessing a database containing information on candidate speakers; questioning the speaker based on the information; receiving, decoding and verifying an answer to the question; obtaining a voice sample of the speaker and verifying the voice sample against a model; generating a score based on the answer and the voice sample; and granting access if the score is equal to or greater than a threshold. Alternatively, the method includes the steps of receiving and decoding speech containing indicia of the speaker; generating a sub-list of speaker candidates having indicia substantially matching the speaker; activating databases containing information about the speaker candidates in the sub-list; performing voice classification analysis; eliminating speaker candidates based on the voice classification analysis; questioning the speaker regarding the information; eliminating speaker candidates based on the answer; and iteratively repeating prior steps until one speaker candidate (in which case the speaker is granted access), or no speaker candidate remains (in which case the speaker is not granted access).

Joint estimation of feature transformation parameters and Gaussian mixture model for speaker identification

The Karhunen–Loève transform is a well-known technique for orthonormally mapping features into an uncorrelated space. The Gaussian mixture model (GMM) with diagonal covariance matrices is a popular technique for modeling the speech feature distributions. These two techniques can be combined to improve the performance of speaker or speech recognition systems. The drawback of the combination is that both set of parameters are not optimized together. This paper presents a new model structure that integrates both orthonormal transformation and diagonal-covariance Gaussian mixture into a unified framework. All parameters of this model are obtained simultaneously by Maximum Likelihood estimation. This idea is further extended to attain a new GMM with generalized covariance matrices (GC–GMM). The traditional GMM with diagonal or full covariance matrices is a special case of the GC–GMM. The proposed method is demonstrated on a 100-person connected digit database for text independent speaker identification. In comparison with the traditional GMM, the computational complexity and the number of parameters can be greatly reduced with no degradation in system performance.

Binary quantization of feature vectors for robust text-independent speaker identification

We present a novel approach to vector quantization in which a feature vector is represented by a binary vector. It is called binary quantization (BQ). The performance criterion of vector quantization, distortion (distance) measure, was employed for investigating the effectiveness of BQ. At 12 b/analysis frame, the average distortion caused by BQ is even lower than the intraspeaker average distance between two repetitions of the same word (after DTW alignment). Since the output of BQ is a binary sequence, it is possible to combine it with a forward Hamming net classifier. In terms of the idea of a hierarchical model for describing a speaker individual characteristics, a text-independent speaker identification system was set up. Experimental results show that the performance of this system is very good. Not only are the small memory space and little computation required, in the speaker identification system, but, more importantly, it shows strong robustness in additive Gaussian white noise.

Robust text-independent speaker identification over telephone channels

This paper addresses the issue of closed-set text-independent speaker identification from samples of speech recorded over the telephone. It focuses on the effects of acoustic mismatches between training and testing data, and concentrates on two approaches: (1) extracting features that are robust against channel variations and (2) transforming the speaker models to compensate for channel effects. First, an experimental study shows that optimizing the front end processing of the speech signal can significantly improve speaker recognition performance. A new filterbank design is introduced to improve the robustness of the speech spectrum computation in the front-end unit. Next, a new feature based on spectral slopes is described. Its ability to discriminate between speakers is shown to be superior to that of the traditional cepstrum. This feature can be used alone or combined with the cepstrum. The second part of the paper presents two model transformation methods that further reduce channel effects. These methods make use of a locally collected stereo database to estimate a speaker-independent variance transformation for each speech feature used by the classifier. The transformations constructed on this stereo database can then be applied to speaker models derived from other databases. Combined, the methods developed in this paper resulted in a 38% relative improvement on the closed-set 30-s training 5-s testing condition of the NIST'95 Evaluation task, after cepstral mean removal.

Speaker identification through use of features selected using genetic algorithm

The authors introduce the use of a genetic algorithm in the reduction of a 24 parameter (12 LPC derived cepstral coefficients + 12 Δ-cepstral coefficients) set to a five, six, seven, eight or ten parameter set, for each speaker in text-independent speaker identification. The experimental results show that there is ~5% increase in the recognition rate when the reduced set of parameters is used.

Methods of Combining Multiple Classifiers with Different Features and Their Applications to Text-Independent Speaker Identification

In practical applications of pattern recognition, there are often different features extracted from raw data which needs recognizing. Methods of combining multiple classifiers with different features are viewed as a general problem in various application areas of pattern recognition. In this paper, a systematic investigation has been made and possible solutions are classified into three frameworks, i.e. linear opinion pools, winner-take-all and evidential reasoning. For combining multiple classifiers with different features, a novel method is presented in the framework of linear opinion pools and a modified training algorithm for associative switch is also proposed in the framework of winner-take-all. In the framework of evidential reasoning, several typical methods are briefly reviewed for use. All aforementioned methods have already been applied to text-independent speaker identification. The simulations show that results yielded by the methods described in this paper are better than not only the individual classifiers' but also ones obtained by combining multiple classifiers with the same feature. It indicates that the use of combining multiple classifiers with different features is an effective way to attack the problem of text-independent speaker identification.

Second-order statistical measures for text-independent speaker identification

This article presents an overview of several measures for speaker recognition. These measures relate to second-order statistical tests, and can be expressed under a common formalism. Alternative formulations of these measures are given and their mathematical properties are studied. In their basic form, these measures are asymmetric, but they can be symmetrized in various ways. All measures are tested in the framework of text-independent closed-set speaker identification, on 3 variants of the TIMIT database (630 speakers): TIMIT (high quality speech), FTIMIT (a restricted bandwidth version of TIMIT) and NTIMIT (telephone quality). Remarkable performances are obtained on TIMIT but the results naturally deteriorate with FTIMIT and NTIMIT. Symmetrization appears to be a factor of improvement, especially when little speech material is available. The use of some of the proposed measures as a reference benchmark to evaluate the intrinsic complexity of a given database under a given protocol is finally suggested as a conclusion to this work.

A Modular and Hybrid Connectionist System for Speaker Identification

This paper presents and evaluates a modular/hybrid connectionist system for speaker identification. Modularity has emerged as a powerful technique for reducing the complexity of connectionist systems, and allowing a priori knowledge to be incorporated into their design. Text-independent speaker identification is an inherently complex task where the amount of training data is often limited. It thus provides an ideal domain to test the validity of the modular/hybrid connectionist approach. To achieve such identification, we develop, in this paper, an architecture based upon the cooperation of several connectionist modules, and a Hidden Markov Model module. When tested on a population of 102 speakers extracted from the DARPA-TIMIT database, perfect identification was obtained.

Large population speaker identification using clean and telephone speech

This paper presents text-independent speaker identification results for varying speaker population sizes up to 630 speakers for both clean, wideband speech, and telephone speech. A system based on Gaussian mixture speaker models is used for speaker identification, and experiments are conducted on the TIMIT and NTIMIT databases. The TIMIT results show large population performance under near-ideal conditions, and the NTIMIT results show the corresponding accuracy loss due to telephone transmission. These are believed to be the first speaker identification experiments on the complete 630 speaker TIMIT and NTIMIT databases and the largest text-independent speaker identification task reported to date. Identification accuracies of 99.5 and 60.7% were achieved on the TIMIT and NTIMIT databases, respectively.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>