Publication Details
Comparison of Keyword Spotting Approaches for Informal Continuous Speech
Schwarz Petr, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Fapšo Michal, Ing. (FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
comparison, keyword spotting, hidden Markov model, long temporal trajectory, phoneme recognizer
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 temporal-pattern (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.
@INPROCEEDINGS{FITPUB7886, author = "Igor Sz\H{o}ke and Petr Schwarz and Luk\'{a}\v{s} Burget and Michal Fap\v{s}o and Martin Karafi\'{a}t and Jan \v{C}ernock\'{y} and Pavel Mat\v{e}jka", title = "Comparison of Keyword Spotting Approaches for Informal Continuous Speech", pages = "633--636", booktitle = "Interspeech'2005 - Eurospeech - 9th European Conference on Speech Communication and Technology", journal = "European Speech Communication", year = 2005, location = "Lisabon, PT", ISSN = "1018-4074", language = "english", url = "https://www.fit.vut.cz/research/publication/7886" }