. .. Automatiques, 94 6.1.1 Le système de reconnaissance de la parole du LIUM dédié à MEDIA

.. .. Résultats,

. .. , 102 6.2.2 Système de compréhension à détection d'erreurs . . . . . . . 103 6.2.3 Combinaison multi-systèmes de compréhension, Gestion et détection d'erreurs de reconnaissance, p.107

. .. De-reconnaissance, Simulation, p.117

.. .. Conclusion,

, Sommaire 7.1 Hiérarchisation des étiquettes : les méta-étiquettes

, 2.1 Potentiel de l'intégration des méta-étiquettes dans le système de compréhension final

. .. Apprentissage, , p.130

, Intégrer plusieurs ensembles de méta-étiquettes, p.132

. .. Conclusion, . .-;-edwin, P. Simonnet, N. Deléglise, Y. Camelin et al., Montréal, Canada. 7-12 Décembre 2015. Présentation poster. JEP 2016 Edwin Simonnet, Paul Deléglise, Nathalie Camelin, Yannick Estève, Présentation orale. JDOC 2017 Edwin Simonnet. Neural Networks for Spoken Language Understanding. 17ème Journée des Doctorants de l'ED STIM, pp.4-8, 2015.

A. , Applying convolutional neural networks concepts to hybrid nn-hmm model for speech recognition, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.4277-4280, 2012.

A. , Deep linguistic processing for spoken dialogue systems, Proc. Workshop on Deep Linguistic Processing, pp.49-56, 2007.

[. Bahdanau, Neural machine translation by jointly learning to align and translate, 2014.

[. Baker, The berkeley framenet project, Proc. COLING-ACL-1998, pp.86-99, 1998.

[. Bansal, Tailoring continuous word representations for dependency parsing, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol.2, pp.809-815, 2014.

L. E. Baum, An inequality and associated maximization technique in statistical estimation for probabilistic functions of markov processes, Inequalities, vol.3, issue.1, pp.1-8, 1972.

[. Ben, J. Jannet, and M. A. , Évaluation adaptative des systèmes de transcription en contexte applicatif, 2015.

S. Bengio and G. Heigold, Word embeddings for speech recognition, INTERSPEECH, pp.1053-1057, 2014.

Y. Bengio, Learning deep architectures for ai, Foundations, vol.2, pp.1-55, 2009.

[. Bengio, A neural probabilistic language model, vol.3, pp.1137-1155, 2003.

[. Bengio, Greedy layer-wise training of deep networks, Advances in Neural Information Processing Systems, vol.19, pp.153-160, 2007.

[. Bengio, Learning long-term dependencies with gradient descent is difficult, IEEE transactions on neural networks, vol.5, issue.2, pp.157-166, 1994.

J. Bergstra and Y. Bengio, Random search for hyper-parameter optimization, Journal of Machine Learning Research, vol.13, pp.281-305, 2012.

[. Boite, Traitement de la parole, Presses polytechniques et universitaires romandes, 1999.

. Bonneau-maynard, Media : a semantically annotated corpus of task oriented dialogs in french, Language Resources and Evaluation, vol.43, issue.4, pp.329-354, 2009.
URL : https://hal.archives-ouvertes.fr/inria-00424619

. Bonneau-maynard, Semantic annotation of the french media dialog corpus, 2005.

L. Bottou, Une approche théorique de l'apprentissage connexionniste : Applications à la reconnaissance de la parole, 1991.

L. Bottou, Large-scale machine learning with stochastic gradient descent, Proceedings of COMPSTAT'2010, pp.177-186, 2010.

F. Bougares, Attelage de systèmes de transcription automatique de la parole, 2012.

[. Brun, Ants : le système de transcription automatique du loria, Workshop Évaluation des Systèmes de Transcription Enrichie d'Émissions Radiophoniques (ESTER'05), 2005.

F. Béchet, Modèles numériques pour la compréhension automatique de la parole, Béchet, 2007.

[. Béchet, Is ATIS too shallow to go deeper for benchmarking Spoken Language Understanding models ? InterSpeech, International Conference on Language Resources and Evaluation (LREC, pp.1-5, 2012.

[. Caglayan, Nmtpy : A flexible toolkit for advanced neural machine translation systems, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01647873

N. Camelin, Stratégies robustes de compréhension de la parole basées sur des méthodes de classification automatique, 2007.

[. Camelin, Detection and Interpretation of Opinion Expressions in Spoken Surveys, IEEE Transactions on Audio, Speech and Language Processing, 2010.
URL : https://hal.archives-ouvertes.fr/hal-01314505

[. Camelin, Unsupervised concept annotation using latent dirichlet allocation and segmental methods, Proceedings of the First Workshop on Unsupervised Learning in NLP, pp.72-81, 2011.
URL : https://hal.archives-ouvertes.fr/hal-01314555

S. F. Chen-et-goodman-;-chen and J. Et-goodman, An empirical study of smoothing techniques for language modeling, Computer Speech & Language, vol.13, issue.4, pp.359-394, 1999.

[. Chen, Syntax or semantics ? knowledge-guided joint semantic frame parsing, IEEE Workshop on Spoken Language Technology, 2016.

[. Cho, Learning phrase representations using rnn encoder-decoder for statistical machine translation, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01433235

[. Cho, On the properties of neural machine translation : Encoder-decoder approaches, 2014.

N. Chomsky and N. Chomsky, Syntactic structures. Mouton, The Hague, 1957.

[. Chorowski, End-to-end continuous speech recognition using attention-based recurrent nn : First results, 2014.

[. Chorowski, Attention-based models for speech recognition, 2015.

W. ;. Collobert, R. Collobert, and J. Weston, A unified architecture for natural language processing : Deep neural networks with multitask learning, Proceedings of the 25th International Conference on Machine Learning, pp.160-167, 2008.

[. Collobert, Natural language processing (almost) from scratch, 2011.

[. Mori and R. , Spoken dialogue with computers, 1998.

D. Mori-;-de-mori and R. , Automatic Speech Recognition & Understanding, ASRU. IEEE Workshop on, pp.365-376, 2007.

. [de-mori, Spoken language understanding, Signal Processing Magazine, vol.25, issue.3, pp.50-58, 2008.
URL : https://hal.archives-ouvertes.fr/hal-01314884

[. Dediu, Statistical Language and Speech Processing : First International Conference, Proceedings. Lecture Notes in Computer Science, 2013.

. Devillers, The french media/evalda project : the evaluation of the understanding capability of spoken language dialogue systems, 2004.

M. Dinarelli, I. Tellier, M. Dinarelli, V. Vukoti?, and C. Raymond, Improving recurrent neural networks for sequence labelling, Label-dependency coding in Simple Recurrent Networks for Spoken Language Understanding, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01489976

. [dubuisson-duplessis, Nao is doing humour in the CHIST-ERA JOKER project. 16th Interspeech, pp.1072-1073, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01206698

J. L. Elman, Finding structure in time, Cognitive science, vol.14, issue.2, pp.179-211, 1990.

C. Fillmore, Frame semantics and the nature of language, Annals of the New York Academy of Sciences, vol.280, issue.1, pp.20-32, 1976.

J. G. Fiscus, 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

J. G. Fiscus, A post-processing system to yield reduced word error rates : Recognizer output voting error reduction (rover), IEEE Workshop on, pp.347-354, 1997.

G. D. Forney-;-forney, The viterbi algorithm, IEEE Transactions on Speech and Audio Processing, vol.61, issue.3, pp.268-278, 1973.

. Fosler-lussier, On the road to improved lexical confusability metrics. ISCA Tutorial and Research Workshop (ITRW) on Pronunciation Modeling and Lexicon Adaptation for Spoken Language Technology, 2002.

[. Galliano, Corpus description of the Ester evaluation campaign for the rich transcription of French broadcast news, 5th international Conference on Language Resources and Evaluation (LREC), pp.315-320, 2006.

[. Galliano, The Ester 2 evaluation campaign for the rich transcription of french radio broadcasts, 2009.

[. Gauvain, The limsi continuous speech dictation system : evaluation on the arpa wall street journal task, IEEE International Conference on Acoustics, Speech and Signal Processing, vol.1, pp.557-560, 1994.

S. Ghannay, Etude sur les representations continues de mots appliquees à la detection automatique des erreurs de reconnaissance de la parole, 2017.
URL : https://hal.archives-ouvertes.fr/tel-01661491

[. Ghannay, End-to-end named entity and semantic concept extraction from speech, IEEE SLT, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01987740

[. Ghannay, Word embeddings combination and neural networks for robustness in asr error detection, Signal Processing Conference (EUSIPCO), pp.1671-1675, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01433210

[. Ghannay, Acoustic word embeddings for asr error detection, pp.1330-1334, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01433176

[. Ghannay, Combining continuous word representation and prosodic features for asr error prediction, International Conference on Statistical Language and Speech Processing, pp.84-95, 2015.

[. Ghannay, Word embedding evaluation and combination, of the Language Resources and Evaluation Conference (LREC 2016), pp.23-28, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01433185

Y. Gong, Speech recognition in noisy environments : A survey, Speech Communication, vol.16, pp.261-291, 1995.

[. Gorin, How may i help you ?, Speech Commun, vol.23, issue.1-2, pp.113-127, 1997.

A. Graves, Generating sequences with recurrent neural networks, 2013.

[. Graves, The ETAPE corpus for the evaluation of speech-based TV content processing in the French language, 2013 IEEE international conference on acoustics, speech and signal processing, pp.114-118, 2012.

[. Griol, A two-stage combining classifier model for the development of adaptive dialog systems, International Journal of Neural Systems, vol.26, issue.01, 2016.

. Grishman, R. Sundheim-;-grishman, and B. Sundheim, Message understanding conference 6 : A brief history, Proc COLING, vol.96, pp.466-471, 1996.

, Structuration automatique de flux télévisuels, 2011.

[. Gupta, The at t spoken language understanding system, IEEE Transactions on Audio, Speech, and Language Processing, vol.14, issue.1, pp.213-222, 2006.

[. Hahn, , 2011.

, Comparing stochastic approaches to spoken language understanding in multiple languages, IEEE Transactions on Audio, Speech, and Language Processing, vol.19, issue.6, pp.1569-1583

[. Hahn, A comparison of various methods for concept tagging for spoken language, 2008.
URL : https://hal.archives-ouvertes.fr/hal-01321122

. Hakkani-tür, Multi-domain joint semantic frame parsing using bi-directional rnn-lstm, Proceedings of The 17th Annual Meeting of the International Speech Communication Association, 2016.

C. ;. Hammersley, J. Hammersley, and P. Clifford, Markov fields on finite graphs and lattices, 1971.

Y. Young-;-he and S. Young, A data-driven spoken language understanding system, IEEE Workshop on Automatic Speech Recognition and Understanding, pp.583-588, 2003.

[. Hemphill, The atis spoken language systems pilot corpus, Proceedings of the DARPA speech and natural language workshop, pp.96-101, 1990.

[. Hinton, Deep neural networks for acoustic modeling in speech recognition : The shared views of four research groups, Signal Processing Magazine, vol.29, issue.6, pp.82-97, 2012.

[. Hinton, Distilling the knowledge in a neural network. NIPS Deep Learning and Representation Learning Workshop, 2015.

[. Hinton, A fast learning algorithm for deep belief nets, Neural computation, vol.18, issue.7, pp.1527-1554, 2006.

S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural computation, vol.9, issue.8, pp.1735-1780, 1997.

J. J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proceedings of the national academy of sciences, vol.79, pp.2554-2558, 1982.

. Huang, Microsoft windows highly intelligent speech recognizer : Whisper, IEEE International Conference on Acoustics, Speech and Signal Processing, vol.1, 1995.

. Iyer, Language modeling with sentence-level mixtures, Proceedings of the Workshop on Human Language Technology, pp.82-87, 1994.

[. Jabaian, Investigating multiple approaches for SLU portability to a new language, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00959197

[. Jaitly, Application of pretrained deep neural networks to large vocabulary speech recognition, Proceedings of Interspeech, 2012.

F. Jelinek-;-jelinek, Continuous speech recognition by statistical methods, Proceedings of the IEEE, vol.64, issue.4, pp.532-556, 1976.

T. Joachims, Text categorization with support vector machines : Learning with many relevant features, Machine Learning : ECML-98, pp.137-142, 1998.

M. I. Jordan, Serial order : A parallel distributed processing approach, Advances in psychology, vol.121, pp.471-495, 1997.

. Juang, B. Juang, and L. Rabiner, Automatic speech recognition -a brief history of the technology development, 2005.

[. Jyothi, P. Fosler-lussier-;-jyothi, and E. Fosler-lussier, Discriminative language modeling using simulated asr errors. Eleventh Annual Conference of the International Speech Communication Association, 2010.

[. Kleinbauer, Combining multiple information layers for the automatic generation of indicative meeting abstracts, Proceedings of the Eleventh European Workshop on Natural Language Generation, pp.151-154, 2007.

[. Lafferty, Conditional random fields : Probabilistic models for segmenting and labeling sequence data, Proceedings of the 18th International Conference on Machine Learning (ICML-2001), vol.1, pp.282-289, 2001.

[. Lailler, Utilisation d'annotations sémantiques pour la validation automatique d'hypothèses dans des conversations téléphoniques, 2015.

[. Lavergne, Practical very large scale CRFs, Proceedings the 48th Annual Meeting of the Association for Computational Linguistics (ACL), pp.504-513, 2010.

[. Lecun, Handwritten digit recognition with a back-propagation network, Advances in neural information processing systems, 1990.

Y. Lecun, A. Lee, and T. Kawahar, Une procedure d'apprentissage pour reseau a seuil asymmetrique (a learning scheme for asymmetric threshold networks), Proc. of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 1985.

[. Lee, Improved acoustic modeling for continuous speech recognition, Workshop on Speech and Natural Language, pp.319-326, 1990.

. Lee, C. M. Narayanan-;-lee, and S. S. Et-narayanan, Toward detecting emotions in spoken dialogs, IEEE Transactions on Speech and Audio Processing, vol.13, issue.2, pp.293-303, 2005.

[. Lefèvre, Leveraging study of robustness and portability of spoken language understanding systems across languages and domains : the PORTMEDIA corpora, The International Conference on Language Resources and Evaluation, 2012.

[. Lefèvre, Robustesse et portabilités multilingue et multi-domaines des systèmes de compréhension de la parole : les corpus du projet portmedia, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol.1, pp.302-308, 2012.

L. ;. Liu, B. Liu, I. Lane, and . Ma, Attention-based recurrent neural network models for joint intent detection and slot filling. CoRR, abs/1609.01454, The 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015.

[. Makhoul, Performance measures for information extraction, Proceedings of DARPA Broadcast News Workshop, pp.249-252, 1999.

R. Malouf and . Mangu, Finding consensus in speech recognition : word error minimization and other applications of confusion networks, International Conference On Computational Linguistics, 1-7. Association for Computational Linguistics Morristown, vol.14, pp.373-400, 2000.

S. R. Maskey, Automatic broadcast news speech summarization, 2008.

[. Mdhaffar, Le corpus PASTEL pour le traitement automatique de cours magistraux. 25e confé-rence sur le Traitement Automatique des Langues Naturelles, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01757775

L. Medsker-et-jain-;-medsker and L. C. Jain, Recurrent neural networks : design and applications, 1999.

R. Memisevic, Gradient-based learning of higher-order image features, International Conference on Computer Vision, pp.1591-1598, 2011.

[. Mesnil, Using recurrent neural networks for slot filling in spoken language understanding, 2015.

, IEEE/ACM Transactions on Audio, Speech and Language Processing, vol.23, issue.3, pp.530-539

[. Mesnil, Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding, INTERSPEECH, pp.3771-3775, 2013.

[. Mikolov, Efficient estimation of word representations in vector space, Proceedings of Workshop at ICLR, 2013.

[. Mikolov, Recurrent neural network based language model. Interspeech, vol.2, p.3, 2010.

[. Mikolov, Extensions of recurrent neural network language model, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5528-5531, 2011.

[. Mikolov, Distributed representations of words and phrases and their compositionality. CoRR, abs/1310, p.4546, 2013.

W. Minker and S. Bennacef, Speech and human-machine dialog, 2004.

M. Minsky and S. A. Papert, , 1969.

M. Mohri, M. Nederhof, J. Jean-claude, N. Et-gertjan, and V. Moreau, Regular approximation of context-free grammars through transformation, Robustness in Language and Speech Technology, pp.153-163, 2000.

S. Acoustics and S. Processing, ICASSP'00. Proceedings. 2000 IEEE International Conference on, vol.3, pp.1807-1810, 2000.

[. Murray, Interpretation and transformation for abstracting conversations, Human Language Technologies : The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp.894-902, 2010.

. Nasr, Macaon : Une chaîne linguistique pour le traitement de graphes de mots. Traitement Automatique des Langues Naturelles -session de démonstrations, 2010.

M. ;. Niekrasz, J. Niekrasz, and J. Moore, Participant subjectivity and involvement as a basis for discourse segmentation, Proceedings of the SIGDIAL 2009 Conference : The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp.54-61, 2009.

. Nocera, Principe et performances du décodeur parole continue speeral, 2002.

. Ogawa, A. Ogawa, and T. Hori, Asr error detection and recognition rate estimation using deep bidirectional recurrent neural networks. Acoustics, Speech and Signal Processing (ICASSP), IEEE International Conference on, pp.4370-4374, 2015.
DOI : 10.1109/icassp.2015.7178796

T. Paek, E. Horvitz, R. J. Passonneau, and D. J. Et-litman, Optimizing automated call routing by integrating spoken dialog models with queuing models, Comput. Linguist, vol.23, issue.1, pp.103-139, 1997.

[. Pennington, Glove : Global vectors for word representation, A speech understanding system based on statistical representation of semantics. ICASSP, vol.12, 1992.
DOI : 10.3115/v1/d14-1162

URL : https://doi.org/10.3115/v1/d14-1162

O. Pietquin and R. Beaufort, Comparing asr modeling methods for spoken dialogue simulation and optimal strategy learning, 2005.

[. Povey, The kaldi speech recognition toolkit, IEEE, 2011.

M. J. Powell-;-powell, A fast algorithm for nonlinearly constrained optimization calculations, Numerical Analysis, pp.144-157, 1978.

L. Rabiner, A tutorial on hidden markov models and selected applications in speech recognition, Proceedings of the IEEE, vol.77, issue.2, pp.257-286, 1989.

L. A. Ramshaw, M. P. Marcus, C. Raymond, C. Raymond, and G. Riccardi, Décodage conceptuel : co-articulation des processus de transcription et compréhension dans les systèmes de dialogue. PhD, 1995.

[. Reddy, Transforming dependency structures to logical forms for semantic parsing, Transactions of the Association for Computational Linguistics, vol.4, pp.127-140, 2016.
DOI : 10.1162/tacl_a_00088

URL : https://doi.org/10.1162/tacl_a_00088

F. Rosenblatt, The perceptron, a perceiving and recognizing automaton project para, 1957.

F. Rosenblatt, The perceptron : a probabilistic model for information storage and organization in the brain, Psychological review, vol.65, issue.6, p.386, 1958.

[. Rousseau, LIUM and CRIM ASR system combination for the REPERE evaluation campaign. International Conference on Text, Speech, and Dialogue, pp.441-448, 2014.
DOI : 10.1007/978-3-319-10816-2_53

URL : https://hal.archives-ouvertes.fr/hal-01450629

Y. D. Rubinstein and T. Hastie, Discriminative vs informative learning, PROC. THIRD INT. CONF. ON KNOWLEDGE DISCOVERY AND DATA MINING, pp.49-53, 1997.

R. Taylor-;-rudy, J. Taylor, and G. W. , Generative classconditional autoencoders, 2014.

[. Rumelhart, Learning internal representations by error propagation, 1985.

[. Rumelhart, Learning representations by back-propagating errors, Nature, vol.323, pp.533-536, 1986.

[. Rumelhart, Learning representations by back-propagating errors, Cognitive modeling, vol.5, issue.3, p.1, 1988.

R. Salakhutdinov-et-hinton-;-salakhutdinov and G. E. Hinton, Deep boltzmann machines, AISTATS, vol.1, p.3, 2009.

[. Juan and S. F. , Exploiting resources from closely-related languages for automatic speech recognition in low-resource languages from Malaysia, 2015.
URL : https://hal.archives-ouvertes.fr/tel-01314120

[. Sarikaya, Application of deep belief networks for natural language understanding, IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), vol.22, issue.4, pp.778-784, 2014.

. Schatzmann, Error simulation for training statistical dialogue systems, ASRU. IEEE Workshop on, pp.526-531, 2007.

. Schaul, No more pesky learning rate, vol.28, pp.343-351, 2013.

M. Schuster and K. Paliwal, Bidirectional recurrent neural networks, IEEE Transactions on Signal Processing, vol.45, issue.11, pp.2673-2681, 1997.

H. Schwenk, Continuous space language models, Computer Speech & Language, vol.21, issue.3, pp.492-518, 2007.
URL : https://hal.archives-ouvertes.fr/hal-01454941

H. Schwenk, Cslm -a modular open-source continuous space language modeling toolkit, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp.1198-1202, 2013.

. Schwenk, Continuous space language models for statistical machine translation, Proceedings of the COLING/ACL on Main Conference Poster Sessions, pp.723-730, 2006.
URL : https://hal.archives-ouvertes.fr/hal-01433882

S. Seneff, Tina : A probabilistic syntactic parser for speech understanding systems, 1989.

[. Serdyuk, Towards end-to-end spoken language understanding, 2018.

. Seymore, K. Rosenfeld-;-seymore, and R. Rosenfeld, Using story topics for language model adaptation, 1997.

[. Simonnet, Exploring the use of attention-based recurrent neural networks for spoken language understanding, Machine Learning for Spoken Language Understanding and Interaction workshop (SLUNIPS), 2015.
URL : https://hal.archives-ouvertes.fr/hal-01433202

[. Stemmer, Comparison and combination of confidence measures, Text Speech and Dialogue, pp.181-188, 2002.

[. Stolcke, Dialogue act modeling for automatic tagging and recognition of conversational speech, 2000.

[. Stuttle, A framework for dialog systems data collection using a simulated asr channel, 2004.

[. Sutskever, Sequence to sequence learning with neural networks, Advances in Neural Information Processing Systems, 2014.

. Tompson, Joint training of a convolutional network and a graphical model for human pose estimation, Advances in Neural Information Processing Systems, vol.27, pp.1799-1807, 2014.

[. Tur-et-de-mori-;-tur, G. Et-de-mori, and R. , Spoken language understanding : Systems for extracting semantic information from speech, 2011.

[. Tur, Model adaptation for dialog act tagging, IEEE Spoken Language Technology Workshop, pp.94-97, 2006.

[. Tur, What is left to be understood in atis ?, IEEE Spoken Language Technology Workshop, pp.19-24, 2010.

[. Turian, Word representations : A simple and general method for semi-supervised learning, Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp.384-394, 2010.

V. Vapnik, Estimation of dependences based on empirical data, 1982.

V. Vapnik, The nature of statistical learning theory, 1995.

[. Vincent, Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th International Conference on Machine Learning, pp.1096-1103, 2008.

[. Vincent, Stacked denoising autoencoders : Learning useful representations in a deep network with a local denoising criterion, J. Mach. Learn. Res, vol.11, pp.3371-3408, 2010.

[. Vukotic, Is it time to switch to word embedding and recurrent neural networks for spoken language understanding ?, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01196915

[. Wang, Is word error rate a good indicator for spoken language understanding accuracy, IEEE Workshop on Automatic Speech Recognition and Understanding, pp.577-582, 2003.

[. Wang, Combining statistical and knowledge-based spoken language understanding in conditional models, COLING/ACL06, pp.882-889, 2006.

[. Wiesler, Rasr/nn : The rwth neural network toolkit for speech recognition, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.3281-3285, 2014.

[. Woodland, The 1997 htk broadcast news transcription system, Workshop DARPA Broadcast News Transcription and Understanding, pp.41-48, 1998.

W. Woods, What's in a link ? Representation and Understanding, 1975.

. Xu, . Sarikaya, P. Xu, and R. Sarikaya, Convolutional neural network based triangular crf for joint intent detection and slot filling, IEEE Workshop on Automatic Speech Recognition and Understanding, pp.78-83, 2013.

[. Yao, Spoken language understanding using long short-term memory neural networks, IEEE Spoken Language Technology Workshop (SLT), pp.189-194, 2014.

[. Yu, Calibration of confidence measures in speech recognition, IEEE Transactions on Audio, Speech, and Language Processing, vol.19, issue.8, pp.2461-2473, 2011.

J. Zbontar and Y. Et-lecun, Stereo matching by training a convolutional neural network to compare image patches, 2015.

M. D. Zeiler-;-zeiler, Adadelta : an adaptive learning rate method, 2012.

[. Zhang, Investigations on ensemble based semi-supervised acoustic model training, Proc. of Eurospeech, Lisbon Portugal, 2005.

[. Zhao, Dialport : Connecting the spoken dialog research community to real user data, 2016.

, TDE : Taux d'erreur de détection des erreurs de reconnaissance WER : Taux d'erreur sur les mots

, Intervalle de confiance Nous considérons pour nos expériences sur le corpus MEDIA un intervalle de confiance à 95% selon la loi de Student pour évaluer la significativité statistique des résultats. -En CER sur le corpus manuel : nous estimons un intervalle de confiance de 1,1 sur le DEV

C. En, nous estimons un intervalle de confiance de 1,3 sur le DEV et de 0,8 sur le TEST. -En CVER sur le corpus automatique : nous estimons un intervalle de confiance de 1,4 sur le DEV