Automatic speech recognition: a study and performance evaluation on neural networks and hidden markov models

• Autor(a) principal: Thomé, Antonio Carlos Gay
• Data de Publicação: 1999
• Outros Autores: Santos, Sidney B. dos, Diniz, Suelaine S
• Tipo de documento: Relatório
• Idioma: eng
• Título da fonte: Repositório Institucional da UFRJ
• Texto Completo: http://hdl.handle.net/11422/2652
• topic: CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO; Reconhecimento de voz; Redes neurais (Ciência da computação)

The main goal in this research is to find out possible ways to built hybrid systems, based on neural network (NN) and hidden M;arkov (HMM) models, for the task of automatic speech recognition. The investigation that has been conducted covers different types of neural network and hidden Markov models, and the combination of them into some hybrid models. The neural networks used were basically MLP and Radial Basis models. The hidden Markov models were basically different combinations of states and mixtures of the Continuous Density type of the Bakis model. A reduced set with ten words spoken in the Portuguese idiom, from Brazil, was carefully chosen to provide some pronounce and phonetic confusion. The results already obtained showed very positive, pointing toward to a high potentiality of such hybrid models.