Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Comparison of Keyword Spotting Approaches for Informal Continuous Speech

Igor Szoke, Petr Schwarz, Pavel Matejka, Lukas Burget, Martin Karafiat, Michal Fapso, Jan Cernocky

Brno University of Technology, Czech Republic

This paper describes several approaches to keyword spotting (KWS) for informal continuous speech. We compare acoustic keyword spotting, spotting in word lattices generated by large vocabulary continuous speech recognition and a hybrid approach making use of phoneme lattices generated by a phoneme recognizer. The systems are compared on carefully defined test data extracted from ICSI meeting database. The acoustic and phoneme-lattice based KWS are based on a phoneme recognizer making use of temporalpattern (TRAP) feature extraction and posterior estimation using neural nets. We show its superiority over traditional HMM/GMM systems. The advantages and drawbacks of different approaches are discussed.

Full Paper

Bibliographic reference.  Szoke, Igor / Schwarz, Petr / Matejka, Pavel / Burget, Lukas / Karafiat, Martin / Fapso, Michal / Cernocky, Jan (2005): "Comparison of keyword spotting approaches for informal continuous speech", In INTERSPEECH-2005, 633-636.