Acoustic Feature Combination for Robust Speech Recognition, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., pp.457-460, 2005. ,
DOI : 10.1109/ICASSP.2005.1415149
Framebased acoustic feature integration for speech understanding, Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing ICASSP, pp.4997-5000, 2008. ,
DOI : 10.1109/icassp.2008.4518780
URL : https://hal.archives-ouvertes.fr/hal-00424663
Frame based system combination and a comparison with weighted ROVER and CNC, ICSLP, 2006. ,
Loosely coupled HMMs for ASR, ICSLP, 2000. ,
Cross-system adaptation and combination for continuous speech recognition: The influence of phoneme set and acoustic front-end, Conference on Speech Communication and Technology, 2006. ,
Complementarity of speech recognition systems and system combination, 2004. ,
Constructing ensembles of ASR systems using randomized decision trees, Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '05), B. Ramabhadran, pp.197-200, 2005. ,
Complementary System Generation using Directed Decision Trees, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, pp.15-20 ,
DOI : 10.1109/ICASSP.2007.366918
A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER), 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings, pp.347-354, 1997. ,
DOI : 10.1109/ASRU.1997.659110
Segmental minimum bayes-risk ASR voting strategies, ICSLP, 2000. ,
DOI : 10.1109/tsa.2004.825678
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.2556
ROVER, Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers on XX, NAACL '07, 2007. ,
DOI : 10.3115/1614108.1614125
Investigations of issues for using multiple acoustic models to improve continuous speech recognition, ICSLP, 2006. ,
Combining multiple speech recognizers using voting and language model information, ICSLP, 2000. ,
Bayesian Model Combination (BAYCOM) for Improved Recognition, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., pp.845-848, 2005. ,
DOI : 10.1109/ICASSP.2005.1415246
Posterior probability decoding, confidence estimation, and system combination, Proceedings NIST Speech Transcription Workshop, 2000. ,
A new framework for system combination based on integrated hypothesis space, Interspeech'06-ICSLP, 2006. ,
System Combination by Driven Decoding, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, pp.341-344, 2007. ,
DOI : 10.1109/ICASSP.2007.366919
URL : https://hal.archives-ouvertes.fr/hal-01318073
Generalized driven decoding for speech recognition system combination, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.1549-1552, 2008. ,
DOI : 10.1109/ICASSP.2008.4517918
URL : https://hal.archives-ouvertes.fr/hal-01318069
Integrating imperfect transcripts into speech recognition systems for building high-quality corpora, Computer Speech & Language, vol.26, issue.2, pp.67-89, 2012. ,
DOI : 10.1016/j.csl.2011.06.001
URL : https://hal.archives-ouvertes.fr/hal-00953675
Comparison between product and mean classifier combination rules, Workshop on Statistical Techniques in Pattern Recognition, 1997. ,
The LIA's French broadcast news transcription system, SWIM: Lectures by Masters in Speech Processing, 2004. ,
Scalable language model lookahead for LVCSR, InterSpeech'05, 2005. ,
Cheating with imperfect transcripts, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96, pp.2115-2118, 1996. ,
DOI : 10.1109/ICSLP.1996.607220
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.4448
The LIUM speech transcription system: A CMU Sphinx III-based system for French broadcast news, Interspeech'05-Eurospeech, 2005. ,
The ESTER phase II evaluation campaign for the rich transcription of French broadcast news, Proc. of the European Conf. on Speech Communication and Technology, 2005. ,
ALIZE, a free toolkit for speaker recognition, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., 2005. ,
DOI : 10.1109/ICASSP.2005.1415219
URL : https://hal.archives-ouvertes.fr/hal-01434280
Combined low-level and highlevel features for out-of-vocabulary word detection, International conference of the Speech Communication Association, ISCA, Inter- Speech'09, 2009. ,
The 1996 Hub-4 Sphinx-3 system, Proceedings of the 1997 ARPA Speech Recognition Workshop, pp.85-89, 1997. ,
Automatic detection of well recognized words in automatic speech transcription, LREC 2006, 2006. ,
URL : https://hal.archives-ouvertes.fr/hal-01434123
Morpho-syntactic post-processing of N-best lists for improved French automatic speech recognition, Computer Speech & Language, vol.24, issue.4, 2010. ,
DOI : 10.1016/j.csl.2009.10.001
URL : https://hal.archives-ouvertes.fr/hal-00508471