A two-stage speech recognition method for information retrieval applications

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 rst 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 rst 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.