Encontrados 4 documentos, a visualizar página 1 de 1
Sistema de apoio ao diagnóstico da doença de Chagas baseado em escalogramas e r...
Souza Neto, João; Carvalho, João Luiz Azevedo de; Rocha, Adson Ferreira da; Junqueira Junior, Luiz Fernando; Nascimento, Francisco Assis de OliveiraIntrodução: A Doença de Chagas é uma endemia rural, prevalente em grande parte da América Central e América do Sul e, aproximadamente, metade dos pacientes contaminados com o parasita Trypanosoma cruzi não apresentam sinais clínicos, eletrocardiográficos e radiológicos de envolvimento cardíaco. Este trabalho, entretanto, propõe uma técnica de auxílio ao diagnóstico da Doença de Chagas baseada em sinais de eletr...
Semi-automatic algorithm for construction of the left ventricular area variatio...
Melo Júnior, Salvador Alves de; Macchiavello Espinoza, Bruno Luiggi; Andrade, Marcelino Monteiro de; Carvalho, João Luiz Azevedo deThe present study was supported by CNPq, a Brazilian government agency for scientific and technological development: “Chamada Conjunta MCT/SEPIN-FINEP-CNPq 01/2002, Programa de Apoio à Pesquisa e Desenvolvimento e Inovação em Tecnologia da Informação PDI - TI”. BM received a M.Sc. fellowship from the Brazilian Ministry of Education (MEC/CAPES).; Background: Two-dimensional echocardiography (2D-echo) allows the ...
Noise-robust speaker recognition using reduced Multiconditional Gaussian Mixtur...
D’Almeida, Frederico Quadros; Nascimento, Francisco Assis de Oliveira; Berger, Pedro de Azevedo; Silva, Lúcio Martins daMulticonditional Modeling is widely used to create noise-robust speaker recognition systems. However, the approach is computationally intensive. An alternative is to optimize the training condition set in order to achieve maximum noise robustness while using the smallest possible number of noise conditions during training. This paper establishes the optimal conditions for a noise-robust training model by consid...
Automatic speaker recognition with Multi-resolution Gaussian Mixture models (MR...
D’Almeida, Frederico Quadros; Nascimento, Francisco Assis de Oliveira; Berger, Pedro de Azevedo; Silva, Lúcio Martins daGaussian Mixture Models (GMMs) are the most widely used technique for voice modeling in automatic speaker recognition systems. In this paper, we introduce a variation of the traditional GMM approach that uses models with variable complexity (resolution). Termed Multi-resolution GMMs (MR-GMMs); this new approach yields more than a 50% reduction in the computational costs associated with proper speaker identifica...