Publication Details

Comparison of Keyword Spotting Approaches for Informal Continuous Speech

SZŐKE Igor, SCHWARZ Petr, MATĚJKA Pavel, BURGET Lukáš, FAPŠO Michal, KARAFIÁT Martin and ČERNOCKÝ Jan. Comparison of Keyword Spotting Approaches for Informal Continuous Speech. In: 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms. Edinburgh, 2005, p. 12.
Czech title
Porovnání metod pro detekci klíčových slov pro neformální plynulou řeč
Type
conference paper
Language
english
Authors
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT)
Schwarz Petr, Ing., Ph.D. (DCGM FIT BUT)
Matějka Pavel, 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, doc. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

comparison, keyword spotting, hidden Markov model, long temporal trajectory, phoneme recognizer

Abstract

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 advantages and drawbacks of different approaches are discussed. 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. A posterior probability transformation function is introduced for posterior based acoustic keyword spotting. We also propose a posterior masking algorithm to speed-up acoustic keyword spotting.

Published
2005
Pages
12
Proceedings
2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms
Conference
2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, Edinburgh, GB
Place
Edinburgh, GB
BibTeX
@INPROCEEDINGS{FITPUB7887,
   author = "Igor Sz\H{o}ke and Petr Schwarz and Pavel Mat\v{e}jka and Luk\'{a}\v{s} Burget and Michal Fap\v{s}o and Martin Karafi\'{a}t and Jan \v{C}ernock\'{y}",
   title = "Comparison of Keyword Spotting Approaches for Informal Continuous Speech",
   pages = 12,
   booktitle = "2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms",
   year = 2005,
   location = "Edinburgh, GB",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/7887"
}
Back to top