Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Phone-Based Prefiltering for Continuous Speech Recognition

Renato De Mori (1), Diego Giuliani (2), Roberto Gretter (2)

(1) Me Gill University School of Computer Science, Montreal, Quebec, Canada
(2) IRST - Istituto per la Ricerca Scientifica e Tecnologica, Povo di Trento, Italy

An architecture for speech recognition is proposed, based on four stages: (1) recognition of the most likely phone sequence using centisecond Hidden Markov Models (HMMs); (2) phone-based lexical and syntactical forward decoding; (3) A*phone-based backward pass, producing a Word Hypothesis Structure (WHS); (4) accurate rescoring of the search sub-space represented by the WHS using centisecond HMMs. Experiments carried out on two different tasks show that a recognizer based on the proposed four-stage architecture is able to achieve comparable performance respect to a classic one-stage recognizer. Experimental results show also that the same recognition performance can be obtained with WHSs built with this approach and WHSs built using centisecond HMMs with a potential speed-up, in WHS generation, proportional to the average phoneme duration in centiseconds.

Full Paper

Bibliographic reference.  Mori, Renato De / Giuliani, Diego / Gretter, Roberto (1994): "Phone-based prefiltering for continuous speech recognition", In ICSLP-1994, 2203-2206.