Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Comparison of Three Approaches to Phonetic String Generation for Large Vocabulary Speech Recognition

Javier Macias-Guarasa, Manuel A. Leandro, Xavier Menendez-Pidal, Jose Colas, Ascension Gallardo, Jose M. Pardo, Santiago Aguilera

Grupo de Tecnologia del Habla, Departamento de Ingenieria Electronica, RT.S.1. de Telecomunicacion, Madrid, Spain

We are building a large vocabulary, isolated word preselection system according to a bottom-up design strategy. It will be used in the development of a dictation machine for Spanish and it is composed of three main modules: feature extraction, phonetic string build up and lexical access. In the second one, we are considering three different technological approaches based on static modeling (SM), Hidden Markov Models (HMM) and Neural Networks (NN). This paper will compare these three alternatives in terms of recognition performance, training complexity and computational load, and will conclude with the results of the comparison in order to adopt the most suitable approach depending on the task.

Full Paper

Bibliographic reference.  Macias-Guarasa, Javier / Leandro, Manuel A. / Menendez-Pidal, Xavier / Colas, Jose / Gallardo, Ascension / Pardo, Jose M. / Aguilera, Santiago (1994): "Comparison of three approaches to phonetic string generation for large vocabulary speech recognition", In ICSLP-1994, 2211-2214.