European Conference on Speech Technology
Edinburgh, Scotland, UK
In this paper, a Speaker-dependent continuous speech recognition system is described. An unknown utterance is recognized by means of the following procedures: acoustic analysis, phonetic segmentation and identification, word and sentence recognition. In order to adjust some of the system parameters, a speaker adaptation module is able to match known utterances with their acoustical representation. The task to be performed is given as a parameter of the system and is described by its vocabulary and its grammar. Recognition results of continuously spoken sentences extracted from a "pseudo-Logo" language are presented.
Bibliographic reference. Mercier, Guy / Bigorgne, D. / Guennec, L. Le / Miclet, Laurent / Monné, Jean / Querre, M. / Vaissière, Jacqueline / Cloatre, M. (1987): "Speaker-dependent continuous speech recognition with KEAL", In ECST-1987, 1009-1012.