Reconhecimento de voz através de unidades menores do que a palavra, utilizando Wavelet Packet e SVM, em uma nova estrutura hierárquica de decisão

The automatic speech recognition by machine has been the target of researchers in the past five decades. In this period have been numerous advances, such as in the field of recognition of isolated words (commands), which has very high rates of recognition, currently. However, we are still far from developing a system that could have a performance similar to the human being (automatic continuous speech recognition). One of the great challenges of searches for continuous speech recognition is the large amount of pattern. The modern languages such as English, French, Spanish and Portuguese have approximately 500,000 words or patterns to be identified. The purpose of this study is to use smaller units than the word such as phonemes, syllables and difones units as the basis for the speech recognition, aiming to recognize any words without necessarily using them. The main goal is to reduce the restriction imposed by the excessive amount of patterns. In order to validate this proposal, the system was tested in the isolated word recognition in dependent-case. The phonemes characteristics of the Brazil s Portuguese language were used to developed the hierarchy decision system. These decisions are made through the use of neural networks SVM (Support Vector Machines). The main speech features used were obtained from the Wavelet Packet Transform. The descriptors MFCC (Mel-Frequency Cepstral Coefficient) are also used in this work. It was concluded that the method proposed in this work, showed good results in the steps of recognition of vowels, consonants (syllables) and words when compared with other existing methods in literature

Sistema inteligente para diagnóstico de patologias na laringe utilizando máquinas de vetor de suporte

The human voice is an important communication tool and any disorder of the voice can have profound implications for social and professional life of an individual. Techniques of digital signal processing have been used by acoustic analysis of vocal disorders caused by pathologies in the larynx, due to its simplicity and noninvasive nature. This work deals with the acoustic analysis of voice signals affected by pathologies in the larynx, specifically, edema, and nodules on the vocal folds. The purpose of this work is to develop a classification system of voices to help pre-diagnosis of pathologies in the larynx, as well as monitoring pharmacological treatments and after surgery. Linear Prediction Coefficients (LPC), Mel Frequency cepstral coefficients (MFCC) and the coefficients obtained through the Wavelet Packet Transform (WPT) are applied to extract relevant characteristics of the voice signal. For the classification task is used the Support Vector Machine (SVM), which aims to build optimal hyperplanes that maximize the margin of separation between the classes involved. The hyperplane generated is determined by the support vectors, which are subsets of points in these classes. According to the database used in this work, the results showed a good performance, with a hit rate of 98.46% for classification of normal and pathological voices in general, and 98.75% in the classification of diseases together: edema and nodules

Classificação de imagens de ambientes coralinos: uma abordagem empregando uma combinação de classificadores e máquina de vetor de suporte

The use of the maps obtained from remote sensing orbital images submitted to digital processing became fundamental to optimize conservation and monitoring actions of the coral reefs. However, the accuracy reached in the mapping of submerged areas is limited by variation of the water column that degrades the signal received by the orbital sensor and introduces errors in the final result of the classification. The limited capacity of the traditional methods based on conventional statistical techniques to solve the problems related to the inter-classes took the search of alternative strategies in the area of the Computational Intelligence. In this work an ensemble classifiers was built based on the combination of Support Vector Machines and Minimum Distance Classifier with the objective of classifying remotely sensed images of coral reefs ecosystem. The system is composed by three stages, through which the progressive refinement of the classification process happens. The patterns that received an ambiguous classification in a certain stage of the process were revalued in the subsequent stage. The prediction non ambiguous for all the data happened through the reduction or elimination of the false positive. The images were classified into five bottom-types: deep water; under-water corals; inter-tidal corals; algal and sandy bottom. The highest overall accuracy (89%) was obtained from SVM with polynomial kernel. The accuracy of the classified image was compared through the use of error matrix to the results obtained by the application of other classification methods based on a single classifier (neural network and the k-means algorithm). In the final, the comparison of results achieved demonstrated the potential of the ensemble classifiers as a tool of classification of images from submerged areas subject to the noise caused by atmospheric effects and the water column

Análise e classificação de imagens de lesões da pele por atributos de cor, forma e textura utilizando máquina de vetor de suporte

The skin cancer is the most common of all cancers and the increase of its incidence must, in part, caused by the behavior of the people in relation to the exposition to the sun. In Brazil, the non-melanoma skin cancer is the most incident in the majority of the regions. The dermatoscopy and videodermatoscopy are the main types of examinations for the diagnosis of dermatological illnesses of the skin. The field that involves the use of computational tools to help or follow medical diagnosis in dermatological injuries is seen as very recent. Some methods had been proposed for automatic classification of pathology of the skin using images. The present work has the objective to present a new intelligent methodology for analysis and classification of skin cancer images, based on the techniques of digital processing of images for extraction of color characteristics, forms and texture, using Wavelet Packet Transform (WPT) and learning techniques called Support Vector Machine (SVM). The Wavelet Packet Transform is applied for extraction of texture characteristics in the images. The WPT consists of a set of base functions that represents the image in different bands of frequency, each one with distinct resolutions corresponding to each scale. Moreover, the characteristics of color of the injury are also computed that are dependants of a visual context, influenced for the existing colors in its surround, and the attributes of form through the Fourier describers. The Support Vector Machine is used for the classification task, which is based on the minimization principles of the structural risk, coming from the statistical learning theory. The SVM has the objective to construct optimum hyperplanes that represent the separation between classes. The generated hyperplane is determined by a subset of the classes, called support vectors. For the used database in this work, the results had revealed a good performance getting a global rightness of 92,73% for melanoma, and 86% for non-melanoma and benign injuries. The extracted describers and the SVM classifier became a method capable to recognize and to classify the analyzed skin injuries

Acoustic feature extraction using perceptual wavelet packet decomposition for frog call classification

Frog protection has become increasingly essential due to the rapid decline of its biodiversity. Therefore, it is valuable to develop new methods for studying this biodiversity. In this paper, a novel feature extraction method is proposed based on perceptual wavelet packet decomposition for classifying frog calls in noisy environments. Pre-processing and syllable segmentation are first applied to the frog call. Then, a spectral peak track is extracted from each syllable if possible. Track duration, dominant frequency and oscillation rate are directly extracted from the track. With k-means clustering algorithm, the calculated dominant frequency of all frog species is clustered into k parts, which produce a frequency scale for wavelet packet decomposition. Based on the adaptive frequency scale, wavelet packet decomposition is applied to the frog calls. Using the wavelet packet decomposition coefficients, a new feature set named perceptual wavelet packet decomposition sub-band cepstral coefficients is extracted. Finally, a k-nearest neighbour (k-NN) classifier is used for the classification. The experiment results show that the proposed features can achieve an average classification accuracy of 97.45% which outperforms syllable features (86.87%) and Mel-frequency cepstral coefficients (MFCCs) feature (90.80%).

Adaptive frequency scaled wavelet packet decomposition for frog call classification

Environmental changes have put great pressure on biological systems leading to the rapid decline of biodiversity. To monitor this change and protect biodiversity, animal vocalizations have been widely explored by the aid of deploying acoustic sensors in the field. Consequently, large volumes of acoustic data are collected. However, traditional manual methods that require ecologists to physically visit sites to collect biodiversity data are both costly and time consuming. Therefore it is essential to develop new semi-automated and automated methods to identify species in automated audio recordings. In this study, a novel feature extraction method based on wavelet packet decomposition is proposed for frog call classification. After syllable segmentation, the advertisement call of each frog syllable is represented by a spectral peak track, from which track duration, dominant frequency and oscillation rate are calculated. Then, a k-means clustering algorithm is applied to the dominant frequency, and the centroids of clustering results are used to generate the frequency scale for wavelet packet decomposition (WPD). Next, a new feature set named adaptive frequency scaled wavelet packet decomposition sub-band cepstral coefficients is extracted by performing WPD on the windowed frog calls. Furthermore, the statistics of all feature vectors over each windowed signal are calculated for producing the final feature set. Finally, two well-known classifiers, a k-nearest neighbour classifier and a support vector machine classifier, are used for classification. In our experiments, we use two different datasets from Queensland, Australia (18 frog species from commercial recordings and field recordings of 8 frog species from James Cook University recordings). The weighted classification accuracy with our proposed method is 99.5% and 97.4% for 18 frog species and 8 frog species respectively, which outperforms all other comparable methods.

Wavelet packet transforms for system-on-chip applications

A methodology for the production of silicon cores for wavelet packet decomposition has been developed. The scheme utilizes efficient scalable architectures for both orthonormal and biorthogonal wavelet transforms. The cores produced from these architectures can be readily scaled for any wavelet function and are easily configurable for any subband structure. The cores are fully parameterized in terms of wavelet choice and appropriate wordlengths. Designs produced are portable across a range of silicon foundries as well as FPGA and PLD technologies. A number of exemplar implementations have been produced.

Feature Extraction Methods Based on Linear Predictive Coding and Wavelet Packet Decomposition for Recognizing Spoken Words in Malayalam

Speech signals are one of the most important means of communication among the human beings. In this paper, a comparative study of two feature extraction techniques are carried out for recognizing speaker independent spoken isolated words. First one is a hybrid approach with Linear Predictive Coding (LPC) and Artificial Neural Networks (ANN) and the second method uses a combination of Wavelet Packet Decomposition (WPD) and Artificial Neural Networks. Voice signals are sampled directly from the microphone and then they are processed using these two techniques for extracting the features. Words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. Training, testing and pattern recognition are performed using Artificial Neural Networks. Back propagation method is used to train the ANN. The proposed method is implemented for 50 speakers uttering 20 isolated words each. Both the methods produce good recognition accuracy. But Wavelet Packet Decomposition is found to be more suitable for recognizing speech because of its multi-resolution characteristics and efficient time frequency localizations

Subspace and wavelet-packet algorithms for de-noising and classifying broadband THz transients

The results from a range of different signal processing schemes used for the further processing of THz transients are contrasted. The performance of different classifiers after adopting these schemes are also discussed.

Classification of lactose and mandelic acid THz spectra using subspace and wavelet-packet algorithms

This work compares classification results of lactose, mandelic acid and dl-mandelic acid, obtained on the basis of their respective THz transients. The performance of three different pre-processing algorithms applied to the time-domain signatures obtained using a THz-transient spectrometer are contrasted by evaluating the classifier performance. A range of amplitudes of zero-mean white Gaussian noise are used to artificially degrade the signal-to-noise ratio of the time-domain signatures to generate the data sets that are presented to the classifier for both learning and validation purposes. This gradual degradation of interferograms by increasing the noise level is equivalent to performing measurements assuming a reduced integration time. Three signal processing algorithms were adopted for the evaluation of the complex insertion loss function of the samples under study; a) standard evaluation by ratioing the sample with the background spectra, b) a subspace identification algorithm and c) a novel wavelet-packet identification procedure. Within class and between class dispersion metrics are adopted for the three data sets. A discrimination metric evaluates how well the three classes can be distinguished within the frequency range 0. 1 - 1.0 THz using the above algorithms.

Aplicação da transformada Wavelet Packet na análise e classificação de sinais de vozes patológicas

o exame para o diagnóstico de doenças da laringe é usualmente realizado através da videolaringoscopia e videoestroboscopia. A maioria das doenças na laringe provoca mudanças na voz do paciente. Diversos índices têm sido propostos para avaliar quantitativamente a qualidade da voz. Também foram propostos vários métodos para classificação automática de patologias da laringe utilizando apenas a voz do paciente. Este trabalho apresenta a aplicação da Transformada Wavelet Packet e do algoritmo Best Basis [COI92] para a classificação automática de vozes em patológicas ou normais. Os resultados obtidos mostraram que é possível classificar a voz utilizando esta Transformada. Tem-se como principal conclusão que um classificador linear pode ser obtido ao se empregar a Transformada Wavelet Packet como extrator de características. O classificador é linear baseado na existência ou não de nós na decomposição da Transformada Wavelet Packet. A função Wavelet que apresentou os melhores resultados foi a sym1et5 e a melhor função custo foi a entropia. Este classificador linear separa vozes normais de vozes patológicas com um erro de classificação de 23,07% para falsos positivos e de 14,58%para falsos negativos.

Classificação de sinais de voz utilizando a transformada Wavelet Packet e redes neurais artificiais

Este trabalho apresenta um sistema de classificação de voz disfônica utilizando a Transformada Wavelet Packet (WPT) e o algoritmo Best Basis (BBA) como redutor de dimensionalidade e seis Redes Neurais Artificiais (ANN) atuando como um conjunto de sistemas denominados “especialistas”. O banco de vozes utilizado está separado em seis grupos de acordo com as similaridades patológicas (onde o 6o grupo é o dos pacientes com voz normal). O conjunto de seis ANN foi treinado, com cada rede especializando-se em um determinado grupo. A base de decomposição utilizada na WPT foi a Symlet 5 e a função custo utilizada na Best Basis Tree (BBT) gerada com o BBA, foi a entropia de Shannon. Cada ANN é alimentada pelos valores de entropia dos nós da BBT. O sistema apresentou uma taxa de sucesso de 87,5%, 95,31%, 87,5%, 100%, 96,87% e 89,06% para os grupos 1 ao 6 respectivamente, utilizando o método de Validação Cruzada Múltipla (MCV). O poder de generalização foi medido utilizando o método de MCV com a variação Leave-One-Out (LOO), obtendo erros em média de 38.52%, apontando a necessidade de aumentar o banco de vozes disponível.