4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Segmental Search for Continuous Speech Recognition

Pietro Laface (1), Luciano Fissore (2), A. Maro (2), Franco Ravera (2)

(1) Dipartimento di Automatica e Informatica - Politecnico di Torino, Torino, Italy
(2) CSELT - Centro Studi e Laboratori Telecomunicazioni, Torino, Italy

The paper illustrates a search strategy for continuous speech recognition based on the recently developed Fast Segmental Viterbi Algorithm (FSVA) [5], a new search strategy particularly effective for very large vocabulary word recognition. The FSVA search has been extended to deal with continuous speech using a network that merges a general lexical tree and a set of bigram subtrees generated on demand during the search. Results are given for a 751-words speaker independent spontaneous speech recognizer of a railway timetable inquiry application, managed by a dialog system. Preliminary tests have been performed on the Wall Street Journal 5K words 1992 evaluation set.

Full Paper

Bibliographic reference.  Laface, Pietro / Fissore, Luciano / Maro, A. / Ravera, Franco (1996): "Segmental search for continuous speech recognition", In ICSLP-1996, 2155-2158.