Accessing Information in Spoken Audio
April 19-20, 1999
This paper reports explorations on a novel approach for speech information retrieval with spoken queries. The method uses a two-layer decoding scheme, where the intermediary representation of speech is based on phonemes, which makes the system vocabulary-independent. Moreover, the use of synchronized lattices at this intermediary level is shown to improve the discriminative performance while decreasing the size of the parameter space, and with a very reasonable additional computational cost.
Full Paper (PDF) Full Paper (Zipped Postscript)
Bibliographic reference. Ferrieux, Alexandre / Peillon, Stephane (1999): "Phoneme-level indexing for fast and vocabulary-independent voice/voice retrieval", In Access-Audio-1999, 60-63.