Sixth European Conference on Speech Communication and Technology (EUROSPEECH'99) Budapest, Hungary September 5-9, 1999

A Two-Stage Speech Recognition Method for Information Retrieval Applications

Paolo Coletti, Marcello Federico

ITC-irst Centro per la Ricerca Scientifica e Tecnologica Povo, Trento, Italy

This paper presents a two-stage approach to speech recognition that is suited for information retrieval tasks, e.g. accessing a large telephone directory. The first stage performs a Viterbi beam search to decode the speech input into a sequence of phonemes. The second stage performs a graph search to match the phoneme sequence with a large list of keywords. The key issue is that the first step employs a syllable based language model that does not necessarily depend on the application domain. Experimental results are shown for a telephone directory access task of one million of entries.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Coletti, Paolo / Federico, Marcello (1999): "A two-stage speech recognition method for information retrieval applications", In EUROSPEECH'99, 459-462.