Language dependent universal phoneme posterior estimation for mixed language speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2011, Pages 5012-5015

  Imseng, David ^a,b   Bourlard, Hervé ^a,b   Magimai Doss, Mathew ^a   Dines, John ^a  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

^b EPFL   (Switzerland)

Author keywords

Acoustic model combination; Mixed language speech recognition; Non native speech; Speech recognition; Universal phoneme set

Indexed keywords

ACOUSTIC MODEL; EUROPEAN LANGUAGES; LANGUAGE ENVIRONMENT; MIXED LANGUAGE SPEECH RECOGNITION; MONOLINGUAL TASKS; NON-NATIVE; POSTERIOR PROBABILITY; POTENTIAL BENEFITS; THEORETICAL FRAMEWORK; UNIVERSAL PHONEME SET;

SIGNAL PROCESSING; SPEECH COMMUNICATION;

SPEECH RECOGNITION;

EID: 80051655273     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947482     Document Type: Conference Paper

References (7)

1. David Imseng, Hervé Bourlard, and Mathew Magimai.-Doss, "Towards mixed language speech recognition systems," in Proc. of Interspeech, 2010, pp. 278-281.
2. Tanja Schultz and Alex Waibel, "Language independent and language adaptive acoustic modeling for speech recognition," Speech Communication, vol. 35, pp. 31-51, 2001.
3. Joachim Köhler, "Multilingual phone models for vocabulary-independent speech recognition tasks," Speech Communication, vol. 35, pp. 21-30, 2001.
4. Dirk Van Compernolle, "Recognizing speech of goats, wolves, sheep and...non-natives," Speech Communication, vol. 35, pp. 71-79, 2001.
5. Michael D. Richard and Richard P. Lippmann, "Neural network classifiers estimate bayesian a posteriori probabilities," Neural Computation, vol. 3, no. 4, pp. 461-483, 1991.
6. David Imseng, Mathew Magimai.-Doss, and Hervé Bourlard, "Hierarchical multilayer perceptron based language identification," in Proc. of Interspeech, 2010, pp. 2722-2725.
7. Martin Raab, Rainer Gruhn, and Elmar Nöth, "Multilingual weighted codebooks for non-native speech recognition," in Proc. of the 11th int. conf. on Text, Speech and Dialogue, 2008, pp. 485-492.