Automatic out-of-language detection based on confidence measures derived from LVCSR word and phone lattices

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2009, Pages 1215-1218

  Motlicek, Petr ^a  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

Author keywords

Confidence measure; LVCSR; Out of language (OOL) detection

Indexed keywords

CONFIDENCE MEASURE; DETECTION ACCURACY; LANGUAGE DETECTION; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; SPEECH SEGMENTS; TARGET LANGUAGE;

CONTINUOUS SPEECH RECOGNITION; LINGUISTICS; QUERY LANGUAGES; TELEPHONE SETS;

SPEECH COMMUNICATION;

EID: 70450190961     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. F. Wessel, R. Schluter, K. Macherey and H. Ney, "Con-fidence measures for large vocabulary continuous speech recognition", in IEEE Trans. Speech and Audio Processing, vol. 9, no. 3, pp. 288298, 2001.
2. G. Bernardis and H. Bourlard, "Improving Posterior Based Confidence Measures in Hybrid HMM/ANN Speech Recognition Systems", in Proc. ICSLP, pp. 775-778, Sydney, Australia, 1998.
3. G. Williams and S. Renals, "Confidence Measures for Hybrid HMM/ANN speech recognition", in Proc. of Eurospeech, pp. 1955-1958, Rhodes, Greece, 1997.
4. L. Burget, et al. "Combination of Strongly and Weakly Constrained Recognizers for Reliable Detection of OOVs", in Proc. of ICASSP, pp. 4081 - 4084, Las Vegas, USA, 2008.
5. H. Ketabdar, M. Hannemann and H. Hermansky, "Detection of Out-of-Vocabulary Words in Posterior Based ASR", in Proc. of Interspeech, pp. 1757-1760, Antwerp, Belgium, 2007.
6. F.Wessel, R. Schluter, H. Ney, "ExplicitWord Error Minimization usingWord Hypothesis Posterior Probabilities", in Proc. of ICASSP, pp. 33-36, Salt Lake City, USA, 2001.
7. C. White, J. Droppo, A. Acero and J. Odel, "Maximum entropy confidence estimation for speech recognition", in Proc. of ICASSP, pp. 809-812, Hawaii, USA, 2007.
8. T. Hain, et al, "The AMI System for the Transcription of Speech in Meetings", in Proc. of ICASSP, pp. 357-360, Hawaii, USA, 2007.
9. Czech University of Technology - data website: 〈http://cmp.felk. cvut.cz/projects/dirac/data/Dirac-CMPdata-16.html〉, and mirror: 〈http://sirius.physik.uni-oldenburg.de/members/bach/〉.