L. Taux-d-'erreur-mot-du-système and .. , du système SPEERAL et du système IRÈNE sur les trois heures issues du corpus de développement, p.70

B. Taux-d-'erreur-mot-par-radio-pour-la-combinaison and L. Celui-du, BONG-SPEERAL) et de l'IRISA (BONG-SPEERAL) avec (P2) et sans (P1) adaptation acoustique, p.74

B. Taux-d-'erreur-mot-global-pour-la-combinaison and L. De-système-du-lium-avec-celui-du, BONG-SPEERAL) et de l'IRISA (BONG-SPEERAL) avec (P2) et sans (P1) adaptation acoustique, p.74

L. Taux-d-'erreur-mot-du-système-du and . Qu, un ROVER sans (Rover-4-2-0-1) et avec (Rover-(4-BONG-2-0-1)) la sortie de la combinaison BONG, p.80

]. Bougares, Y. Estève, P. Deléglise, M. Rouvier, and G. Linarès, Avancées dans le domaine de la transcription automatique par décodage guidé, pp.4-09, 2012.

A. Rousseau, F. Bougares, P. Deléglise, and H. Schwenk, Yannick Estève : LIUM's systems for the IWSLT 2011 Speech Translation Tasks, IWSLT, pp.8-9, 2011.

Y. Estève, P. Deléglise, S. Meignier, S. Petitrenaud, H. Schwenk et al., Some recent research work at LIUM based on the use of CMU Sphinx, Mars 13, 2010.

]. Dufour, F. Bougares, Y. Estève, and P. Deléglise, Unsupervised model adaptation on targeted speech segments for LVCSR system combination, Interspeech, vol.2010, pp.26-30, 2010.
URL : https://hal.archives-ouvertes.fr/hal-01433900

]. Bougares and L. Besacier, Hervé Blanchon : LIG approach for IWSLT09 : Using Multiple Morphological Segmenters for Spoken Language Translation of Arabic Amélioration de la combinaison de systèmes de reconnaissance de la parole par décodage guidé, IWSLT, pp.25-27, 2009.

J. Tasos-anastasakos, R. Mcdonough, J. Schwartz, and . Makhoul, A compact model for speaker-adaptive training, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96, pp.1137-1140, 1996.
DOI : 10.1109/ICSLP.1996.607807

A. Xavier and L. Aubert, An overview of decoding techniques for large vocabulary continuous speech recognition, Computer Speech & Language, vol.16, issue.1, pp.89-114, 2002.

E. Leonard, T. Baum, and . Petrie, Statistical inference for probabilistic functions of finite state Markov chains, Annals of Mathematical Statistics, vol.37, pp.1554-1563, 1966.

]. Bougares, Y. Estève, P. Deléglise, and G. Linarès, Bag of n-gram driven decoding for LVCSR system harnessing, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, pp.11-15, 2011.
DOI : 10.1109/ASRU.2011.6163944
URL : https://hal.archives-ouvertes.fr/hal-01434931

]. Bougares, M. Rouvier, Y. Estève, and G. Linarès, Low latency combination of parallelized single-pass LVCSR systems, In Interspeech, 2012.
URL : https://hal.archives-ouvertes.fr/hal-01313238

C. Breslin, J. F. Mark, and . Gales, Generating complementary systems for speech recognition, Interspeech, 2006.

C. Breslin, J. F. Mark, and . Gales, Directed decision trees for generating complementary systems, Speech Communication, vol.51, issue.3, pp.284-295, 2009.
DOI : 10.1016/j.specom.2008.09.004
URL : https://hal.archives-ouvertes.fr/hal-00499235

F. Peter, P. V. Brown, R. L. Desouza, V. J. Mercer, J. C. Pietra et al., Class-Based n-gram Models of Natural Language, Computational Linguistics, vol.18, issue.23, pp.467-479, 1992.

]. Burget, Measurement of Complementarity of Recognition Systems, Proceedings of the 5th International Conference on Text, Speech and Dialogue, pp.283-290, 2004.
DOI : 10.1007/978-3-540-30120-2_36

F. Stanley, J. Chen, and . Goodman, An empirical study of smoothing techniques for language modeling, Computer Speech and Language, pp.359-394, 1999.

]. Chen and L. Lee, A new framework for system combination based on integrated hypothesis space, Interspeech, 2006.

]. Chong, G. Friedland, A. Janin, N. Morgan, and C. Oei, Opportunities and challenges of parallelizing speech recognition, Proceedings of the 2nd USENIX conference on Hot topics in parallelism, pp.2010-85, 2010.

B. Steven, P. Davis, and . Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences Readings in speech recognition, pp.65-74, 1990.

P. Deléglise, Y. Estève, S. Meignier, and T. Merlin, The LIUM Speech Transcription System : a CMU Sphinx IIIbased System for French Broadcast News, Interspeech 2005, pp.1653-1656, 2005.

P. Deléglise, Y. Estève, S. Meignier, and T. Merlin, Improvements to the LIUM French ASR system based on CMU sphinx : what helps to significantly reduce the word error rate ? In Interspeech, pp.2123-2126, 2009.

]. A. Dempster, N. M. Laird, and D. B. Rubin, Maximum Likelihood from Incomplete Data via the EM Algorithm, Journal of the Royal Statistical Society, vol.39, pp.1-38, 1977.

P. W. Daniel and . Ellis, Stream combination before and/or after the acoustic model, ICASSP, pp.1635-1638, 2000.

P. Estève, B. Deléglise, and . Jacob, Systèmes de transcription automatique de la parole et logiciels libres, Traitement Automatique des Langues, vol.37, 2004.

J. Thierry-bazillon and . Antoine, Frédéric Béchet et Jérôme Farinas. The EPAC corpus : manual and automatic annotations of conversational speech in French broadcast news, LREC 2010, Malta, pp.17-23, 2010.

]. G. Evermann and P. C. Woodland, Posterior Probability Decoding , Confidence Estimation And System Combination, Proceedings NIST Speech Transcription Workshop, 2000.

]. Federico, L. Bentivogli, M. Paul, and S. Stüker, Overview of the IWSLT 2011 Evaluation Campaign, Proceedings of the International Workshop on Spoken Language Translation (IWSLT), 2011.

]. J. Fiscus, A post-prcessing system to yield reduced word error rates : Recogniser Output Voting Error Reduction (ROVER), ASRU, pp.347-354, 1997.

]. Freund and R. E. Schapire, A decision-theoretic generalization of on-linelearning and an application to boosting, European Conference on Computational Learning Theory (EUROCOLT), Mars 1995. (Cité en, p.47, 1995.

]. M. Gales, The Generation And Use Of Regression Class Trees For Mllr Adaptation, 1996.

]. M. Gales and P. C. Woodland, Mean and variance adaptation within the MLLR framework, Computer Speech & Language, vol.10, issue.4, pp.249-264, 1996.
DOI : 10.1006/csla.1996.0013

]. M. Gales, Maximum likelihood linear transformations for HMM-based speech recognition, Computer Speech & Language, vol.12, issue.2, pp.75-98, 1998.
DOI : 10.1006/csla.1998.0043

]. M. Gales, D. Y. Kim, P. C. Woodland, H. Y. Chan, D. Mrva et al., Progress in the CU-HTK broadcast news transcription system, IEEE transactions speech and audio processing, 2006.
DOI : 10.1109/TASL.2006.878264

S. Galliano, E. Geoffrois, G. Gravier, J. F. Bonastre, D. Mostefa et al., Corpus description of the ESTER Evaluation Campaign for the Rich Transcription of French Broadcast News, Proceedings of the 5th Intl. Conf. on Language Resources and Evaluations, 2006.

]. Gu, J. Xue, X. Cui, and Y. Gao, Highperformance low-latency speech recognition via multi-layered feature streaming and fast Gaussian computation, Interspeech, pp.2098-2101, 2008.

]. R. Haeb-umbach and H. Ney, Linear discriminant analysis for improved large vocabulary continuous speech recognition, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp.13-16, 1992.
DOI : 10.1109/ICASSP.1992.225984

]. Hart, N. Nilsson, and B. Raphael, A Formal Basis for the Heuristic Determination of Minimum Cost Paths, IEEE Transactions on Systems Science and Cybernetics, vol.4, issue.2, pp.100-107, 1968.
DOI : 10.1109/TSSC.1968.300136

]. D. Hillard, B. Hoffmeister, M. Ostendorf, R. Schlüter, and H. Ney, 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, pp.65-68, 2007.
DOI : 10.3115/1614108.1614125

]. Hoffmeister, T. Klein, R. Schlüter, and H. Ney, Frame based system combination and a comparison with weighted ROVER and CNC, Interspeech, 2006.

]. Huet, G. Gravier, and P. Sébillot, Morphosyntactic Processing of N-Best Lists for Improved Recognition and Confidence Measure Computation, Eurospeech'07, pp.1741-1744, 2007.

]. R. Iyer and M. Ostendorf, Modeling long distance dependence in language: topic mixtures vs. dynamic cache models, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96, pp.236-239, 1996.
DOI : 10.1109/ICSLP.1996.607085

]. F. Jelinek-1977a, R. L. Jelinek, L. R. Mercer, J. K. Bahl, and . Baker, Perplexity???a measure of the difficulty of speech recognition tasks, The Journal of the Acoustical Society of America, vol.62, issue.S1, p.63, 1977.
DOI : 10.1121/1.2016299

]. Jelinek, Continuous speech recognition, ACM SIGART Bulletin, issue.61, pp.33-34, 1977.
DOI : 10.1145/1045283.1045302

F. Jelinek and R. L. Mercer, Interpolated estimation of Markov source parameters from sparse data, Proceedings, Workshop on Pattern Recognition in Practice. Amsterdam, 1980.

H. Stephan-kanthak, M. Ney, M. Riley, and . Mohri, A comparison of two LVR search optimization techniques, Interspeech, 2002.

R. Kneser and H. Ney, Improved clustering techniques for class-based statistical language modeling, Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), 1993.

]. R. Kneser and H. Ney, Improved backing-off for M-gram language modeling, 1995 International Conference on Acoustics, Speech, and Signal Processing, pp.22-41, 1995.
DOI : 10.1109/ICASSP.1995.479394

]. K. Knill, M. J. Gales, and S. J. Young, Use of Gaussian selection in large vocabulary continuous speech recognition using HMMS, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96, 1996.
DOI : 10.1109/ICSLP.1996.607156

]. R. Kuhn and R. D. Mori, A cache-based natural language model for speech recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.12, issue.6, p.53, 1990.
DOI : 10.1109/34.56193

]. Lamel, J. Gauvain, G. Adda, C. Barras, E. Bilinski et al., The LIMSI 2006 TC-STAR EPPS Transcription Systems, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07, pp.123-128, 2006.
DOI : 10.1109/ICASSP.2007.367240

]. R. Lau, R. Rosenfeld, and S. Roukos, Trigger-based language models: a maximum entropy approach, IEEE International Conference on Acoustics Speech and Signal Processing, pp.45-48, 1993.
DOI : 10.1109/ICASSP.1993.319225

G. Benjamin-lecouteux, P. Linarès, J. Nocera, and . Bonastre, Imperfect transcript driven speech recognition, ICSLP /Interspeech, pp.62-66, 2006.

G. Benjamin-lecouteux, Y. Linarès, J. Estève, and . Mauclair, System Combination by Driven Decoding, ICASSP, 2007. (Cité en pages 8, pp.66-67, 2007.

]. Lecouteux, Reconnaissance automatique de la parole guidée par des transcriptions a priori, 2008.

G. Benjamin-lecouteux, Y. Linarès, G. Estève, and . Gravier, Generalized driven decoding for speech recognition system combination, ICASSP, 2008.

]. C. Leggetter and P. C. Woodland, Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models, Computer Speech & Language, vol.9, issue.2, pp.171-185, 1995.
DOI : 10.1006/csla.1995.0010

]. Li, R. Singh, and R. M. Stern, Combining search spaces of heterogeneous recognizers for improved speech recognition, Proc. ICSLP, 2002.

]. Liu, M. J. Gales, C. Philip, and . Woodland, Use of contexts in language model interpolation and adaptation, Interspeech, pp.360-363, 2009.
DOI : 10.1016/j.csl.2012.06.004

]. Liu, M. J. Gales, C. Philip, and . Woodland, Language model cross adaptation for LVCSR system combination, Interspeech, pp.342-345, 2010.
DOI : 10.1016/j.csl.2012.07.010

]. Liu, M. J. Gales, C. Philip, and . Woodland, Improving LVCSR System Combination Using Neural Network Language Model Cross Adaptation, Interspeech, pp.2857-2860, 2011.

]. J. Lööf, C. Gollan, S. Hahn, G. Heigold, B. Hoffmeister et al., The RWTH 2007 TC-STAR Evaluation System for European English and Spanish, Interspeech, 2007.

]. Mangu, E. Brill, and A. Stolcke, Finding Consensus Among Words : Lattice-Based Word Error Minimization, Proc. Eurospeech, pp.495-498, 1999.
DOI : 10.1006/csla.2000.0152
URL : http://arxiv.org/abs/cs/0010012

E. John, A. H. Markel, and . Gray, Linear prediction of speech, 1982.

F. Mehryar-mohri, M. Pereira, and . Riley, Weighted finite-state transducers in speech recognition, Computer Speech & Language, vol.16, issue.1, pp.69-88, 2002.
DOI : 10.1006/csla.2001.0184

P. Nocera, C. Fredouille, G. Linarès, D. Matrouf, S. Meignier et al., The LIA's French broadcast news transcription system, SWIM : Lectures by Masters in Speech Processing, 2004.

]. S. Ortmanns, A. Eiden, H. Ney, and N. Coenen, Look-Ahead Techniques for Fast Beam Search, ICASSP, 1997.

]. S. Ortmanns, H. Ney, and A. Eiden, Language-model look-ahead for large vocabulary speech recognition, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96, pp.2095-2098, 1998.
DOI : 10.1109/ICSLP.1996.607215

]. M. Ostendorf, A. Kannan, S. Auagin, and O. Kimball, Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses, Proceedings of the workshop on Speech and Natural Language , HLT '91, pp.83-87, 1991.
DOI : 10.3115/112405.112416

]. D. Pallett, W. Fisher, and J. Fiscus, Tools for the analysis of benchmark speech recognition tests, International Conference on Acoustics, Speech, and Signal Processing, pp.97-100, 1990.
DOI : 10.1109/ICASSP.1990.115546

D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek et al., The Kaldi Speech Recognition Toolkit, IEEE 2011 ASRU, Décembre 2011. (Cité en, p.27, 2011.

]. Psutka, L. Müller, and J. V. Psutka, Comparison of MFCC and PLP parameterizations in the speaker independent continuous speech recognition task, Interspeech, pp.1813-1816, 2001.

R. Lawrence and . Rabiner, Readings in speech recognition In A tutorial on hidden Markov models and selected applications in speech recognition, pp.267-296, 1990.

A. Rousseau, F. Bougares, and P. Deléglise, Holger Schwenk et Yannick Estève Overview of the IWSLT 2011 Evaluation Campaign. In LIUM's systems for the IWSLT 2011 Speech Translation Tasks, 2011.

M. Murat-saraclar, E. Riley, V. Bocchieri, and . Goffin, Towards automatic closed captioning : low latency real time broadcast news transcription, Interspeech. ISCA, 2002.

]. R. Schapire, The boosting approach to machine learning : An overview. Nonlinear Estimation and Classification, 2003.

]. Schwenk and J. Gauvain, Combining multiple speech recognizers using voting and language model information, Interspeech, pp.915-918, 2000.

]. Singh, M. L. Seltzer, B. Raj, and R. M. Stern, Speech in Noisy Environments: robust automatic segmentation, feature extraction, and hypothesis combination, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221), pp.273-276, 2001.
DOI : 10.1109/ICASSP.2001.940820

B. Olivier-siohan, B. Ramabhadran, and . Kingsbury, Constructing ensembles of ASR systems using randomized decision trees, IEEE ICASSP, pp.197-200, 2005.

]. Stemmer, S. Steidl, E. Nöth, H. Niemann, and A. Batliner, Comparison and Combination of Confidence Measures, Proceedings of the 5th International Conference on Text, Speech and Dialogue, pp.181-188, 2002.
DOI : 10.1007/3-540-46154-X_25

]. S. Stüker, S. Fügen, M. Burger, and . Wölfel, Cross-System Adaptation and Combination for Continuous Speech Recognition : The Influence of Phoneme Set and Acoustic Front-End ? In Interspeech, p.53, 2006.

S. Suh, H. Kim, and . Kim, Compensating Acoustic Mismatch Using Class-Based Histogram Equalization for Robust Speech Recognition, EURASIP Journal on Advances in Signal Processing, vol.2007, issue.1, 2007.
DOI : 10.1016/S0167-6393(00)00048-0

Y. Takehito-utsuro, T. Kodama, H. Watanabe, S. Nishizaki, and . Nakagawa, Combining outputs of multiple LVCSR models by machine learning, Septembre 2005. (Cité en, pp.9-15, 2005.
DOI : 10.1002/scj.20340

]. V. Valtchev, J. J. Odell, P. C. Woodland, and S. J. Young, MMIE training of large vocabulary recognition systems, Speech Communication, vol.22, issue.4, pp.303-314, 1997.
DOI : 10.1016/S0167-6393(97)00029-0

]. Venkataramani and W. Byrne, Lattice Segmentation and Support Vector Machines for Large Vocabulary Continuous Speech Recognition, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., pp.817-820, 2005.
DOI : 10.1109/ICASSP.2005.1415239

]. A. Viterbi, Error bounds for convolutional codes and an asymptotically optimum decoding algorithm, IEEE Transactions on Information Theory, vol.13, issue.2, 1967.

]. Wessel, R. Schlüter, K. Macherey, and H. Ney, Confidence measures for large vocabulary continuous speech recognition, IEEE Transactions on Speech and Audio Processing, vol.9, issue.3, pp.288-298, 2001.
DOI : 10.1109/89.906002

. Li, H. Yongxin, Y. Erdogan, E. Gao, and . Marcheret, Incremental on-line feature space MLLR adaptation for telephony speech recognition, Interspeech, 2002.

L. Zouari, Vers le temps réel en transcription automatique de la parole grand vocabulaire. These, Télécom ParisTech, 2007.