Ferramentas e recursos livres para reconhecimento e síntese de voz em português brasileiro

Sistemas de reconhecimento e síntese de voz são constituídos por módulos que dependem da língua e, enquanto existem muitos recursos públicos para alguns idiomas (p.e. Inglês e Japonês), os recursos para Português Brasileiro (PB) ainda são escassos. Outro aspecto é que, para um grande número de tarefas, a taxa de erro dos sistemas de reconhecimento de voz atuais ainda é elevada, quando comparada à obtida por seres humanos. Assim, apesar do sucesso das cadeias escondidas de Markov (HMM), é necessária a pesquisa por novos métodos. Este trabalho tem como motivação esses dois fatos e se divide em duas partes. A primeira descreve o desenvolvimento de recursos e ferramentas livres para reconhecimento e síntese de voz em PB, consistindo de bases de dados de áudio e texto, um dicionário fonético, um conversor grafema-fone, um separador silábico e modelos acústico e de linguagem. Todos os recursos construídos encontram-se publicamente disponíveis e, junto com uma interface de programação proposta, têm sido usados para o desenvolvimento de várias novas aplicações em tempo-real, incluindo um módulo de reconhecimento de voz para a suíte de aplicativos para escritório OpenOffice.org. São apresentados testes de desempenho dos sistemas desenvolvidos. Os recursos aqui produzidos e disponibilizados facilitam a adoção da tecnologia de voz para PB por outros grupos de pesquisa, desenvolvedores e pela indústria. A segunda parte do trabalho apresenta um novo método para reavaliar (rescoring) o resultado do reconhecimento baseado em HMMs, o qual é organizado em uma estrutura de dados do tipo lattice. Mais especificamente, o sistema utiliza classificadores discriminativos que buscam diminuir a confusão entre pares de fones. Para cada um desses problemas binários, são usadas técnicas de seleção automática de parâmetros para escolher a representaçãao paramétrica mais adequada para o problema em questão.

An automatic methodology for obtaining optimum shape factors for the radial point interpolation method

In this letter, a methodology is proposed for automatically (and locally) obtaining the shape factor c for the Gaussian basis functions, for each support domain, in order to increase numerical precision and mainly to avoid matrix inversion impossibilities. The concept of calibration function is introduced, which is used for obtaining c. The methodology developed was applied for a 2-D numerical experiment, which results are compared to analytical solution. This comparison revels that the results associated to the developed methodology are very close to the analytical solution for the entire bandwidth of the excitation pulse. The proposed methodology is called in this work Local Shape Factor Calibration Method (LSFCM).

DESIGN OF MICROIRRIGATION SYSTEMS IN SLOPING LANDS USING LINEAR PROGRAMMING

Quando a área a ser irrigada apresenta um elevado gradiente de declive na direção das linhas de derivação, uma opção de dimensionamento é o uso de tubulações com vários diâmetros para economizar no custo e também para manter a variação de pressão dentro dos limites desejados. O objetivo deste trabalho foi desenvolver um modelo de programação linear para dimensionar sistemas de irrigação por microaspersão com linhas de derivação com mais de um diâmetro e operando em declive, visando a minimização do custo anualizado da rede hidráulica e do custo anual com energia elétrica, além de assegurar que a máxima variação de carga hidráulica na linha será respeitada. Os dados de entrada são: configuração da rede hidráulica do sistema de irrigação, custo de todos os componentes da rede hidráulica e custo da energia. Os dados de saída são: custo anual total, diâmetro da tubulação em cada linha do sistema, carga hidráulica em cada ponto de derivação e altura manométrica total. Para ilustrar a potencialidade do modelo desenvolvido, ele foi aplicado em um pomar de citros no Estado de São Paulo, Brasil. O modelo demonstrou ser eficiente no dimensionamento do sistema de irrigação quanto à obtenção da uniformidade de emissão desejada. O custo anual com bombeamento deve ser considerado no dimensionamento de sistemas de irrigação por microaspersão porque ele gera menores valores de custo anual total quando comparado com a mesma alternativa que não considera aquele custo.

Teds-easy - descrição automática de transducer electronic data sheet

Pós-graduação em Engenharia Elétrica - FEIS

Automatic Orientation of Multi-Scale Terrestrial Images for 3D Reconstruction

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

An automatic method for segmentation of fission tracks in epidote crystal photomicrographs

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

A genetic algorithm/mathematical programming approach to solve a two-level soft drink production problem

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Extração de contornos de telhado de edifícios no espaço-objeto baseada em snakes e programação dinâmica a partir de TIN/laser e imagens aéreas de alta resolução

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Development of a CAD system for automatic classification of microcalcifications based on FPGA

This paper presents a Computer Aided Diagnosis (CAD) system that automatically classifies microcalcifications detected on digital mammograms into one of the five types proposed by Michele Le Gal, a classification scheme that allows radiologists to determine whether a breast tumor is malignant or not without the need for surgeries. The developed system uses a combination of wavelets and Artificial Neural Networks (ANN) and is executed on an Altera DE2-115 Development Kit, a kit containing a Field-Programmable Gate Array (FPGA) that allows the system to be smaller, cheaper and more energy efficient. Results have shown that the system was able to correctly classify 96.67% of test samples, which can be used as a second opinion by radiologists in breast cancer early diagnosis. (C) 2013 The Authors. Published by Elsevier B.V.

A Fuzzy Goal Programming model for solving aggregate production-planning problems under uncertainty: A case study in a Brazilian sugar mill

This paper proposes a Fuzzy Goal Programming model (FGP) for a real aggregate production-planning problem. To do so, an application was made in a Brazilian Sugar and Ethanol Milling Company. The FGP Model depicts the comprehensive production process of sugar, ethanol, molasses and derivatives, and considers the uncertainties involved in ethanol and sugar production. Decision-makings, related to the agricultural and logistics phases, were considered on a weekly-basis planning horizon to include the whole harvesting season and the periods between harvests. The research has provided interesting results about decisions in the agricultural stages of cutting, loading and transportation to sugarcane suppliers and, especially, in milling decisions, whose choice of production process includes storage and logistics distribution. (C)2014 Elsevier B.V. All rights reserved.

A mixed-integer quadratically-constrained programming model for the distribution system expansion planning

This paper presents a mixed-integer quadratically-constrained programming (MIQCP) model to solve the distribution system expansion planning (DSEP) problem. The DSEP model considers the construction/reinforcement of substations, the construction/reconductoring of circuits, the allocation of fixed capacitors banks and the radial topology modification. As the DSEP problem is a very complex mixed-integer non-linear programming problem, it is convenient to reformulate it like a MIQCP problem; it is demonstrated that the proposed formulation represents the steady-state operation of a radial distribution system. The proposed MIQCP model is a convex formulation, which allows to find the optimal solution using optimization solvers. Test systems of 23 and 54 nodes and one real distribution system of 136 nodes were used to show the efficiency of the proposed model in comparison with other DSEP models available in the specialized literature. (C) 2014 Elsevier Ltd. All rights reserved.

Automatic visual dictionary generation through optimum-path forest clusteringautomatic visual dictionary generation through optimum-path forest clustering

Image categorization by means of bag of visual words has received increasing attention by the image processing and vision communities in the last years. In these approaches, each image is represented by invariant points of interest which are mapped to a Hilbert Space representing a visual dictionary which aims at comprising the most discriminative features in a set of images. Notwithstanding, the main problem of such approaches is to find a compact and representative dictionary. Finding such representative dictionary automatically with no user intervention is an even more difficult task. In this paper, we propose a method to automatically find such dictionary by employing a recent developed graph-based clustering algorithm called Optimum-Path Forest, which does not make any assumption about the visual dictionary's size and is more efficient and effective than the state-of-the-art techniques used for dictionary generation.

FROM FACTORY-FLOOR TO UNIVERSITY

The interaction between industry and university is often discussed. Industry participants feel they do not have enough time to spend with academics because of tight deadlines to achieve your goals. The other hand, professors and his students do not have availability and resources for responding quickly to industry activities. Both sides recognize the associated problems and feel the consequences of various forms. One way to reduce the distance between them is to provide industrial labs that resemble the factory floor at the university. Thus not only students may work on a real technological base, but also the industry's problems can be brought to the university laboratory. To ensure that relevant industrial problems will be studied, the industry needs help in the formulation of the problem being researched. The graduate program of Automation and Control Engineering from UNESP Sorocaba is aimed at training human resources with skills in automation and control activities related to the development of automatic control processes, integrating electronic commands, intelligent manufacturing and industrial robotics. In order to achieve its objectives, one of the pillars of the university consists of a wide range of modern equipments and software for industrial automation, which allows the circuit assembly from most primitive until configuration and programming of a complex system of integrated manufacturing. This paper describes industrial automation equipments and laboratory structure offered to students of Control and Automation Engineering graduate program at UNESP Sorocaba as alternative to close technologies and real problems on the job until academic world. The strategic is to do students understand theory and operations in robotic and industrial automation by means to manipulating real production systems locate at university

The Automatic Mapping of Princeton WordNet Lexical-Conceptual Relations onto the Brazilian Portuguese WordNet Database

Princeton WordNet (WN.Pr) lexical database has motivated efficient compilations of bulky relational lexicons since its inception in the 1980's. The EuroWordNet project, the first multilingual initiative built upon WN.Pr, opened up ways of building individual wordnets, and interrelating them by means of the so-called Inter-Lingual-Index, an unstructured list of the WN.Pr synsets. Other important initiative, relying on a slightly different method of building multilingual wordnets, is the MultiWordNet project, where the key strategy is building language specific wordnets keeping as much as possible of the semantic relations available in the WN.Pr. This paper, in particular, stresses that the additional advantage of using WN.Pr lexical database as a resource for building wordnets for other languages is to explore possibilities of implementing an automatic procedure to map the WN.Pr conceptual relations as hyponymy, co-hyponymy, troponymy, meronymy, cause, and entailment onto the lexical database of the wordnet under construction, a viable possibility, for those are language-independent relations that hold between lexicalized concepts, not between lexical units. Accordingly, combining methods from both initiatives, this paper presents the ongoing implementation of the WN.Br lexical database and the aforementioned automation procedure illustrated with a sample of the automatic encoding of the hyponymy and co-hyponymy relations.