Small group speaker identification with common password phrases

A model-based framework of classification error rate estimation is proposed for speech and speaker recognition. It aims at predicting the run-time performance of a hidden Markov model (HMM) based recognition system for a given task vocabulary and grammar without the need of running recognition experiments using a separate set of testing samples. This is highly desirable both in theory and in practice. However, the error rate expression in HMM-based speech recognition systems has no closed form solution due to the complexity of the multi-class comparison process and the need for dynamic time warping to handle various speech patterns. To alleviate the difficulty, we propose a one-dimensional model-based misclassification measure to evaluate the distance between a particular model of interest and a combination of many of its competing models. The error rate for a class characterized by the HMM is then the value of a smoothed zero-one error function given the misclassification measure. The overall error rate of the task vocabulary could then be computed as a function of all the available class error rates. The key here is to evaluate the misclassification measure in terms of the parameters of environmental-matched models without running recognition experiments, where the models are adapted by very limited data that could be just the testing utterance itself. In this paper, we show how the misclassification measure could be approximated by first computing the distance between two mixture Gaussian densities, then between two HMMs with mixture Gaussian state observation densities and finally between two sequences of HMMs. The misclassification measure is then converted into classification error rate. When comparing the error rate obtained in running actual experiments and that of the new framework, the proposed algorithm accurately estimates the classification error rate for many types of speech and speaker recognition problems. Based on the same framework, it is also demonstrated that the error rate of a recognition system in a noisy environment could also be predicted.

Our earlier frame margin probability discriminative training (FMPDT) algorithm has shown its advantage over maximum likelihood estimation (MLE) on multi-condition speech recognition. This paper reports our recent improvement on FMPDT and compares it with minimum classification error (MCE) and minimum phone error (MPE). We rewrite the re-estimation formulae of MCE, MPE in a unified linear interpolation way which facilitates this comparison. We compare the recognition results for MCE and MPE, FMPDT using the Aurora2 standard database and HTK3.4, and find the proposed method can give more balanced improvements under different conditions than other discriminative training algorithms.

In recent years, person reidentification has received growing attention with the increasing popularity of intelligent video surveillance. This is because person reidentification is critical for human tracking with multiple cameras. Recently, keep it simple and straightforward (KISS) metric learning has been regarded as a top level algorithm for person reidentification. The covariance matrices of KISS are estimated by maximum likelihood (ML) estimation. It is known that discriminative learning based on the minimum classification error (MCE) is more reliable than classical ML estimation with the increasing of the number of training samples. When considering a small sample size problem, direct MCE KISS does not work well, because of the estimate error of small eigenvalues. Therefore, we further introduce the smoothing technique to improve the estimates of the small eigenvalues of a covariance matrix. Our new scheme is termed the minimum classification error-KISS (MCE-KISS). We conduct thorough validation experiments on the VIPeR and ETHZ datasets, which demonstrate the robustness and effectiveness of MCE-KISS for person reidentification.

In our previous work, we have proposed a speaker modeling technique using spectral and pitch features for text-independent speaker identification based on Multi-Space Probability Distribution Gaussian Mixture Models (MSD-GMMs). We have presented a maximum likelihood (ML) estimation procedure for the MSD-GMM parameters and demonstrated its high recognition performance. In this paper, we describe an minimum classification error (MCE) training procedure for the MSDGMM speaker models. MCE training is also applied to automatically estimate mixture-dependent stream weights for spectral and pitch streams. The MCE-based MSD-GMM speaker models are evaluated for a text-independent speaker identification task. Experimental results show that MCE training of the MSD-GMM parameters significantly reduces identification errors and system performance is further improved by appropriately weighting spectral and pitch streams using MCE training.

A new look at discriminative training for hidden Markov models

A new large margin nearest neighborhood metric learning (LMNN) method for i-vector based speaker verification is proposed in this paper. In general, a verification decision is taken by computing the cosine distance between the i-vectors of the test utterance and the claimed identity. LMNN metric is learned from the examples and can be viewed as a linear transformation of the input i-vector space of the training and test utterance. In this work, the metric is learned with the objective of reducing the distance between the i-vectors of same class of speaker, while impostors are separated by a large margin. The metric learned in this manner leads to a better speaker verification performance. Speaker verification experiments are then conducted on the NIST 2008 and YOHO speaker verification databases. Experimental results indicate a reasonable improvement in performance, when compared to i-vector based speaker verification methods which use conventional cosine scoring.

This paper considers both the garbage modelling and the discriminative training of a speech recognition system consisting of a multilayer perceptron (MLP) network and hidden Markov models (HMMs). The string level training of the system is based on Minimum Classification Error (MCE) algorithm using especially the ideas recently proposed by Reichl et al. In order to improve the MCE training scheme, they defined a derivative for MCE cost function putting heavier weight to the misclassified utterances than the traditional translated sigmoidal. In this paper, we give a definition of a new cost function, whose derivative has similar properties as the one proposed by Reichl et al. The new and the sigmoidal cost function are compared with the string level (MCE) algorithm. The string recognition rates show that both methods achieve equal performances, but the convergence of the MCE algorithm is a bit faster with the new cost function. Moreover, the performance of two garbage models, the nth best and an interpolative garbage model, are also compared in this paper. The latter one is an approximation of the former one requiring less operations, but achieving comparable performance. The recognition system achieved 93.32% accuracy for test set at best. The test set contained 29188 Finnish digit strings from two environments.

This paper proposes a method of facial expression recognition based on Zernike moments and the minimum classification error (MCE) based hidden Markov model (HMM). In the feature extraction of face, the method of Zernike moments feature extraction based on local feature regions is adopted. First, eyes and mouths are segmented from the facial expression image and Zernike moments feature vectors of eyes and mouth are extracted. In the classification of expression, using MCE criteria is adopted to improve the performance of HMM. The results show that the performance of expression recognition system can be improved to some extent by using Zernike moments and MCE criterion.

The minimum classification error (MCE) framework for discriminative training is a simple and general formalism for directly optimizing recognition accuracy in pattern recognition problems. The framework applies directly to the optimization of hidden Markov models (HMMs) used for speech recognition problems. However, few if any studies have reported results for the application of MCE training to large-vocabulary, continuous-speech recognition tasks. This article reports significant gains in recognition performance and model compactness as a result of discriminative training based on MCE training applied to HMMs, in the context of three challenging large-vocabulary (up to 100 k word) speech recognition tasks: the Corpus of Spontaneous Japanese lecture speech transcription task, a telephone-based name recognition task, and the MIT Jupiter telephone-based conversational weather information task. On these tasks, starting from maximum likelihood (ML) baselines, MCE training yielded relative reductions in word error ranging from 7% to 20%. Furthermore, this paper evaluates the use of different methods for optimizing the MCE criterion function, as well as the use of precomputed recognition lattices to speed up training. An overview of the MCE framework is given, with an emphasis on practical implementation issues

Minimum classification error (MCE) based discriminative methods have been extensively studied and successfully applied to automatic speech recognition, speaker recognition, and utterance verification. Our goal is to modify the embedded string model based MCE algorithm to handle the case of a large number of cross-syllable trip hones used in a large vocabulary recognition system. A selective strategy about MCE based discriminative training method, in particular for Mandarin speech syllable loop recognition, is introduced. We use a syllable loop recognition task to evaluate the performance of the acoustic model of an established large vocabulary continuous speech recognition system. The basic idea is that since decoding errors occur in parts of the models in whole decoded sentences, it is reasonable to adjust the parameters of the wrong models. As a result, a weighted MCE formulation is derived, which can provide more effective convergence and about a 10% error rate reduction for a large training set. Our experiments show that, although the performance of the recognition system is improved, some original correct recognition results are misrecognized after discriminative training, and a divide and conquer strategy is proposed as a solution. Thus, the acoustic feature space is divided into two or more sub-spaces according to the discriminative training procedure. By combining these two methods, we obtain over 14.5% error rate reduction in syllable loop recognition.

In this paper we compare three frameworks for discriminative training of continuous-density hidden Markov models (CD-HMMs). Specifically, we compare two popular frameworks, based on conditional maximum likelihood (CML) and minimum classification error (MCE), to a new framework based on margin maximization. Unlike CML and MCE, our formulation of large margin training explicitly penalizes incorrect decodings by an amount proportional to the number of mislabeled hidden states. It also leads to a convex optimization over the parameter space of CD-HMMs, thus avoiding the problem of spurious local minima. We used discriminatively trained CD-HMMs from all three frameworks to build phonetic recognizers on the TIMIT speech corpus. The different recognizers employed exactly the same acoustic front end and hidden state space, thus enabling us to isolate the effect of different cost functions, parameterizations, and numerical optimizations. Experimentally, we find that our framework for large margin training yields significantly lower error rates than both CML and MCE training.

In this paper, a framework of minimum classification error (MCE) model adaptation for continuous density HMMs is proposed based on the approach of super string model. We show that the error rate minimization in the proposed approach can be formulated into maximizing a special ratio of two positive functions, and from that a general growth transform algorithm is derived for MCE based model adaptation. This algorithm departs from the generalized probability descent (GPD) algorithm, and it is well suited for model adaptation with a small amount of training data. The proposed approach is applied to linear regression based variance adaptation, and the close form solution for variance adaptation using MCE linear regression (MCELR) is derived. The MCELR approach is evaluated on large vocabulary speech recognition tasks. The relative performance gain is more than doubled on the standard (WSJ Spoke 3) database, comparing to maximum likelihood linear regression (MLLR) based variance adaptation for the same amount of adaptation data.

A talker verification system based on characterizing talker utterances as sequences of subword units represented by hidden Markov models (HMMs) was implemented and tested. Two types of subword units were studied: phonelike units (PLUs) and acoustic segment units (ASUs). PLUs are based on phonetic transcriptions of spoken utterances and ASUs are extracted directly from the acoustic signal without use of any linguistic knowledge. The ASU representation has the advantage of not requiring transcriptions of training utterances. Verification performance was evaluated on a 100-talker database of 20000 isolated digit utterances. The experiments show only small differences in performance between PLU- and ASU-based representations. Overall, the verification equal-error rate is approximately 7 to 8% for one-digit test utterances (approximately 0.5 s in duration) and 1% or less for seven-digit test utterances (approximately 3.5 s in duration). In addition, a technique for updating models, using data from current test utterances, was devised and implemented. Using this adaptation technique, the error rate falls to 6% for one-digit utterances and less than 0.5% for seven-digit utterances. The experiment confirms that excellent verification performance can be obtained using HMMs of subword units. >

The goal of this communication is to present a weighted likelihood discriminant for minimum error shape classification. Different from traditional maximum likelihood (ML) methods in which classification is carried out based on probabilities from independent individual class models as is the case for general hidden Markov model (HMM) methods, our proposed method utilizes information from all classes to minimize classification error. Proposed approach uses a hidden Markov model as a curvature feature based 2D shape descriptor. In this contribution we present a generalized probabilistic descent (GPD) method to weight the curvature likelihoods to achieve a discriminant function with minimum classification error. In contrast with other approaches, a weighted likelihood discriminant function is introduced. We believe that our sound theory based implementation reduces classification error by combining hidden Markov model with generalized probabilistic descent theory. We show comparative results obtained with our approach and classic maximum-likelihood calculation for fighter planes in terms of classification accuracies

A comparative study of RPCL and MCE based discriminative training methods for LVCSR