Treinamento discriminativo de HMMs cont?nuos para reconhecimento de palavras isoladas

• Autor(a) principal: Mattos, Amarildo Martins de
• Data de Publicação: 2003
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Biblioteca Digital de Teses e Dissertações da INATEL
• Texto Completo: http://tede.inatel.br:8080/tede/handle/tede/88
• topic: Reconhecimento de fala; reconhecimento de palavras isoladas; modelos ocultos de Markov; treinamento discriminativo; crit?rio MCE; Engenharia - Telecomunica??es

Introduction: speech recognition technology in the present world, objectives of this work, dissertation structure; Hidden Markov models and the ML criterion: Hidden Markov models: HMM elements, 3 HMM problems, isolated word recognition using HMMs; Discriminant training and the MMI criterion: MMI criterion, GPD segmental algorithm: steps for implementation, re-estimation of HMM parameters according to segmental GPD algorithm, normalization of parameters, summary of discriminative training algorithm for isolated words; System implemented: introduction, databases: Inatel and DECOM-UNICAMP database, developed system: Markov models for vocabulary words, parameters, training and recognition module, numerical problems due to normalization constants; Tests and analysis of the results: initial tests, determination of the learning step, determination of the number of training times, order of presentation of the locutions, determination of the set of locutions for the discriminative training