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.
Cite as: Coletti, P., Federico, M. (1999) A two-stage speech recognition method for information retrieval applications. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 459-462, doi: 10.21437/Eurospeech.1999-118
@inproceedings{coletti99_eurospeech,
author={Paolo Coletti and Marcello Federico},
title={{A two-stage speech recognition method for information retrieval applications}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={459--462},
doi={10.21437/Eurospeech.1999-118}
}