EFFICIENT METHODS FOR DETECTING KEYWORDS IN CONTINUOUS SPEECH

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 259-262

  Junkawitsch, Jochen ^a   Ruske, Günther ^b   Höge, Harald ^a  

^a SIEMENS AG   (Germany)

^b TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION; SPEECH RECOGNITION;

CONFIDENCE MEASURE; CONTINUOUS SPEECH; DECODING ALGORITHM; FURTHER DEVELOPMENT; SEARCH PROCEDURES;

VITERBI ALGORITHM;

EID: 1642290854     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. J. Junkawitsch, L. Neubauer, H. Höge and G. Ruske. A new keyword spotting algorithm with precalculated optimal thresholds. Proc. ICSLP, pp. 2067-2070, 1996.
2. M. Weintraub. Keyword-spotting using SRI's DECIPHER large-vocabulary speech-recognition system. Proc. IEEE ICASSP, vol. 2, pp. 463-466, 1993.
3. H. Bourlard, B. D'hoore and J.-M. Boite. Optimizing recognition and rejection performance in wordspotting systems. Proc. IEEE ICASSP, vol. 1, pp. 373-376, 1994.
4. E. Lleida and R. C. Rose. Likelihood ratio decoding and confidence measures for continuous speech recognition. Proc. ICSLP, pp. 478-481, 1996.
5. see the following URL's: http://www.phonetik.uni-muenchen.de/SpeechDat.htmlhttp://www.icp.grenet.fr/ELRA/home.html