Leandro Daniel Vignolo

Feature selection for face recognition based on multi-objective evolutionary wrappers

Abstract Feature selection is a key issue in pattern recognition, specially when prior knowledge of the most discriminant features is not available. Moreover, in order to perform the classification task with reduced complexity and acceptable performance, usually features that are irrelevant, redundant, or noisy are excluded from the problem representation. This work presents a multi-objective wrapper, based on genetic algorithms, to select the most relevant set of features for face recognition tasks. The proposed strategy explores the space of multiple feasible selections in order to minimize the cardinality of the feature subset, and at the same time to maximize its discriminative capacity. Experimental results show that, in comparison with other state-of-the-art approaches, the proposed approach allows to improve the classification performance, while reducing the representation dimensionality.

Genetic wavelet packets for speech recognition

Highlights? A set of features based on wavelet packets was optimized for speech recognition. ? A wrapper for feature selection was designed by means of a genetic algorithm. ? A non-orthogonal representation was obtained, which allowed to increase classification performance. ? The optimized features improved the classification results in noise conditions. The most widely used speech representation is based on the mel-frequency cepstral coefficients, which incorporates biologically inspired characteristics into artificial recognizers. However, the recognition performance with these features can still be enhanced, specially in adverse conditions. Recent advances have been made with the introduction of wavelet based representations for different kinds of signals, which have shown to improve the classification performance. However, the problem of finding an adequate wavelet based representation for a particular problem is still an important challenge. In this work we propose a genetic algorithm to evolve a speech representation, based on a non-orthogonal wavelet decomposition, for phoneme classification. The results, obtained for a set of spanish phonemes, show that the proposed genetic algorithm is able to find a representation that improves speech recognition results. Moreover, the optimized representation was evaluated in noise conditions.

Evolutionary splines for cepstral filterbank optimization in phoneme classification

Mel-frequency cepstral coefficients have long been the most widely used type of speech representation. They were introduced to incorporate biologically inspired characteristics into artificial speech recognizers. Recently, the introduction of new alternatives to the classic mel-scaled filterbank has led to improvements in the performance of phoneme recognition in adverse conditions. In this work we propose a new bioinspired approach for the optimization of the filterbanks, in order to find a robust speech representation. Our approach—which relies on evolutionary algorithms—reduces the number of parameters to optimize by using spline functions to shape the filterbanks. The success rates of a phoneme classifier based on hidden Markov models are used as the fitness measure, evaluated over the well-known TIMIT database. The results show that the proposed method is able to find optimized filterbanks for phoneme recognition, which significantly increases the robustness in adverse conditions.

Evolutionary cepstral coefficients

Evolutionary algorithms provide flexibility and robustness required to find satisfactory solutions in complex search spaces. This is why they are successfully applied for solving real engineering problems. In this work we propose an algorithm to evolve a robust speech representation, using a dynamic data selection method for reducing the computational cost of the fitness computation while improving the generalisation capabilities. The most commonly used speech representation are the mel-frequency cepstral coefficients, which incorporate biologically inspired characteristics into artificial recognizers. Recent advances have been made with the introduction of alternatives to the classic mel scaled filterbank, improving the phoneme recognition performance in adverse conditions. In order to find an optimal filterbank, filter parameters such as the central and side frequencies are optimised. A hidden Markov model is used as the classifier for the evaluation of the fitness for each individual. Experiments were conducted using real and synthetic phoneme databases, considering different additive noise levels. Classification results show that the method accomplishes the task of finding an optimised filterbank for phoneme recognition, which provides robustness in adverse conditions.

Empirical Mode Decomposition for adaptive AM-FM analysis of Speech

The nonlinearity of the speech production system is discussed.The limitations of conventional speech processing methods like LP analysis, STFT and the MFCCs, are discussed.The motivation, principle and methodology of AM-FM analysis is discussed.Empirical Mode Decomposition (EMD) is presented as an adaptive method of AM-FM analysis of speech.Various aspects of EMD are discussed. The developments of EMD are presented.The utilization of EMD in speech processing applications is discussed. This work reviews the advancements in the non-conventional analysis of speech signals, particularly from an AM-FM analysis point of view. The benefits of such an analysis, as opposed to the traditional short-time analysis of speech, is illustrated in this work. The inherent non-linearity of the speech production system is discussed. The limitations of Fourier analysis, Linear Prediction (LP) analysis, and the Mel Filterbank Cepstral Coefficients (MFCCs), are presented, thus providing the motivation for the AM-FM representation of speech. The principle and methodology of traditional AM-FM analysis is discussed, as a method of capturing the non-linear dynamics of the speech signal. The technique of Empirical Mode Decomposition (EMD) is then introduced as a means of performing adaptive AM-FM analysis of speech, alleviating the limitations of the fixed analysis provided by the traditional AM-FM methodology. The merits and demerits of EMD with respect to traditional AM-FM analysis is discussed. The developments of EMD to counter its demerits are presented. Selected applications of EMD in speech processing are briefly reviewed. The paper concludes by pointing out some aspects of speech processing where EMD might be explored.

An evolutionary wrapper for feature selection in face recognition applications

Active shape models is an adaptive shape-matching technique that has been used for locating facial features in images. However, when a number of features is extracted for each landmark point, distortions caused by noise or illumination, and the dimensionality of the final representation, have a negative impact in the performance of a classifier. In this paper, an evolutionary wrapper for selection of the most relevant set of features for face recognition is presented. The proposed strategy explores the space of multiple feasible selections using genetic algorithms. Experimental results show that the proposed approach allows to improve the classification performance in comparison with another enhanced method and a state of the art face recognition approach.

Feature optimisation for stress recognition in speech

An evolutionary algorithm for the optimisation of filter banks.Filter banks more appropriate to stress and emotion classification were obtained.New speech features were obtained through optimised filter banks.The optimised features improved the results in stressed speech classification. Mel-frequency cepstral coefficients introduced biologically-inspired features into speech technology, becoming the most commonly used representation for speech, speaker and emotion recognition, and even for applications in music. While this representation is quite popular, it is ambitious to assume that it would provide the best results for every application, as it is not designed for each specific objective. This work proposes a methodology to learn a speech representation from data by optimising a filter bank, in order to improve results in the classification of stressed speech. Since population-based metaheuristics have proved successful in related applications, an evolutionary algorithm is designed to search for a filter bank that maximises the classification accuracy. For the codification, spline functions are used to shape the filter banks, which allows reducing the number of parameters to optimise. The filter banks obtained with the proposed methodology improve the results in stressed and emotional speech classification.

Multi-objective optimisation of wavelet features for phoneme recognition

State-of-the-art speech representations provide acceptable recognition results under optimal conditions, though their performance in adverse conditions still needs to be improved. In this direction, many advances involving wavelet processing have been reported, showing significant improvements in classification performance for different kinds of signals. However, for speech signals, the problem of finding a convenient wavelet-based representation is still an open challenge. This study proposes the use of a multi-objective genetic algorithm for the optimisation of a wavelet-based representation of speech. The most relevant features are selected from a complete wavelet packet decomposition in order to maximise phoneme classification performance. Classification results for English phonemes, in different noise conditions, show significant improvements compared with well-known speech representations.

Automatic classification of Furnariidae species from the Paranaense Littoral region using speech-related features and machine learning

Over the last years, researchers have addressed the automatic classification of calling bird species. This is important for achieving more exhaustive environmental monitoring and for managing natural resources. Vocalisations help to identify new species, their natural history and macro-systematic relations, while computer systems allow the bird recognition process to be sped up and improved. In this study, an approach that uses state-of-the-art features designed for speech and speaker state recognition is presented. A method for voice activity detection was employed previous to feature extraction. Our analysis includes several classification techniques (multilayer perceptrons, support vector machines and random forest) and compares their performance using different configurations to define the best classification method. The experimental results were validated in a cross-validation scheme, using 25 species of the family Furnariidae that inhabit the Paranaense Littoral region of Argentina (South America). The results show that a high classification rate, close to 90%, is obtained for this family in this Furnariidae group using the proposed features and classifiers.

Coherent averaging estimation autoencoders applied to evoked potentials processing

The success of machine learning algorithms strongly depends on the feature extraction and data representation stages. Classification and estimation of small repetitive signals masked by relatively large noise usually requires recording and processing several different realizations of the signal of interest. This is one of the main signal processing problems to solve when estimating or classifying P300 evoked potentials in brain-computer interfaces. To cope with this issue we propose a novel autoencoder variation, called Coherent Averaging Estimation Autoencoder with a new multiobjective cost function. We illustrate its use and analyze its performance in the problem of event related potentials processing. Experimental results showing the advantages of the proposed approach are finally presented.