Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

A Fast Version of the Atros System

M. J. Castro (1), D. Llorens (2), Joan-Andreu Sánchez (1), F. Casacuberta (1), P. Aibar (2), E. Segarra (1)

(1) Depto. de Sist. Informáticos y Computación, Universitat Politécnica de Valéncia Cami de Vera s/n, Valéncia, Spain
(2) Unidad Predepartamental de Informática, Universitat Jaume I Campus, Castelló, Spain

Atros is an automatic speech recognition/understanding/translation system whose knowledge sources (acoustic models, lexical models, syntactic language models, semantic models and translation models) can be learnt automatically from training data by using similar techniques. The search process in Atros is performed through a Synchronous Beam Search technique. In this paper, a faster version of Atros is presented and evaluated. This version supports improved acoustic and syntactical models. It also incorporates improved search algorithms to reduce and the computational requirements for decoding: Fast Phoneme Look-Ahead and Histogram Pruning. The system has been tested on a Spanish task of queries to a geographical database (with a vocabulary of 1,264 words). The best result achieved (in real time) was 7.10% of word error rate.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Castro, M. J. / Llorens, D. / Sánchez, Joan-Andreu / Casacuberta, F. / Aibar, P. / Segarra, E. (1999): "A fast version of the atros system", In EUROSPEECH'99, 1239-1242.