Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

On the Development of a Dictation Machine for Spanish: DIVO

Javier Macias-Guarasa, Manuel A. Leandro, Jose Colas, Alvaro Villegas, Santiago Aguilera, Jose M. Pardo

Grupo de Tecnologia del Habla, Departamento de Ingenieria Electronica. E.T.S.I. de Telecomunicacion, Madrid, Spain

The first prototype of a low cost dictation machine for Spanish is described (DIVO). The main characteristics of our recognition approach are: bottom-up, hypothesis-verification strategy; large vocabulary, speaker dependent, isolated word recognition. Its modular structure is the cue for quick development and testing of different implementation alternatives. Two of them are presented: one is based in Static phoneme Modeling (SM) and the other uses Discrete Hidden Markov Modeling (DHMM). The system runs on a standard PC compatible (286 or higher) equipped with a DSP board and is fully voice controlled. This first version of the system can address multiple vocabulary sets of up to 2000 words each, with immediate response and reasonable performance. Modules for increasing vocabulary and performance are being developed.

Full Paper

Bibliographic reference.  Macias-Guarasa, Javier / Leandro, Manuel A. / Colas, Jose / Villegas, Alvaro / Aguilera, Santiago / Pardo, Jose M. (1994): "On the development of a dictation machine for Spanish: DIVO", In ICSLP-1994, 1343-1346.