Browse by topic
Type of publication
A Fast Version of the Atros System. European Conference on Speech Communication and Technology. EUROSPEECH'99, 1999. pp. 1299-1302.Atros is an automatic speech recognition/under standing/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 pre sented and evaluated. This version supports im proved acoustic and syntactical models. It also in corporates improved search algorithms to reduce and the computational requirements for decoding: Fast Phoneme LookAhead 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.