International Journals

  • Benjamin Lecouteux, Georges Linarès, Yannick Estève, Guillaume Gravier: “Dynamic Combination of Automatic Speech Recognition Systems by Driven Decoding”, in Journal of IEEE Transactions on Audio, Speech and Language Processing, accepted in 2012.
  • Benjamin Lecouteux, Georges Linarès and Stanislas Oger : Integrating imperfect transcripts into speech recognition systems for building high-quality corpora. In Computer Speech and Language, 2012, 26(2): 67-89 (2012).

International Conferences

  • Bogdan Ludusan, Stefan Ziegler, Guillaume Gravier. Is stress information robust for ASR in adverse conditions?, IEEE International Conference on Acoustics, Speech and Signal Processing, 2013
  • Stefan Ziegler and Bogdan Ludusan and Guillaume Gravier. Integrating acoustic-phonetic landmarks based on articulatory feature streams into HMM speech recognition, IEEE International Conference on Acoustics, Speech and Signal Processing, 2013
  • Fethi Bougares, Mickael Rouvier, Yannick Estève, Georges Linarès: “Low latency combination of parallelized single-pass LVCSR systems”. Interspeech, Portland, Oregon(USA), 9-13 sept. 2012
  • Mohamed Bouallègue, Mickael Rouvier, Driss Matrouf, Georges Linarès : Subspace Gaussian Mixture Models Based on Noise Compensation for Speech Recognition In International conference of the Speech Communication Association, ISCA, InterSpeech'12, Portland, USA, 2012.
  • Mohamed Bouallègue, Driss Matrouf, Emmanuel Ferreira, Georges Linarès, Maria Goudi, Pascal Nocera : Acoustic modeling for under-resourced languages based on vectorial HMM-states representation using subspace gaussian mixture models. In IEEE Speech and Language Technology Workshop (SLT), Miami, USA, 2012.
  • Stefan Ziegler, Bogdan Ludusan, Guillaume Gravier. Towards a new speech event detection approach for landmark-based speech recognition, IEEE Workshop on Spoken Language Technology, 2012
  • Stefan Ziegler and Bogdan Ludusan and Guillaume Gravier. Using broad phonetic classes to guide search in automatic speech recognition. Annual Conference of the International Speech Communication Association, 2012
  • Bogdan Ludusan and Stefan Ziegler and Guillaume Gravier. Integrating Stress Information in Large Vocabulary Continuous Speech Recognition. Annual Conference of the International Speech Communication Association, 2012
  • Rousseau A, Bougares F, Deléglise P, Schwenk H, Estève Y: “LIUM’s systems for the IWSLT 2011 Speech Translation Tasks. International Workshop on Spoken Language Translation In IWSLT”, San Francisco(USA), 8-9 Sept 2011
  • Bougares F, EstèveY, Deléglise P, Linarès G: “Bag of n-gram driven decoding for LVCSR system harnessing”. Automatic speech recognition and Understanding Workshop , Hawaï(USA), 11-15 December 2011
  • B. Lecouteux, P. Nocéra, G. Linarès: “Semantic cache model driven speech recognition”, IEEE ICASSP 2010, Dallas, USA
  • R. Dufour, F. Bougares, Y. Estève, P. Deléglise: “Unsupervised model adaptation on targeted speech segments for LVCSR system combination”, ISCA Interspeech 2010, Makuhari (Japan)

French-speaking Conferences

  • Bougares F, Estève Y, Deléglise P, Rouvier M, Linarès G . Avancées dans le domaine de la transcription automatique par décodage guidé. JEP , Grenoble(France) 2012
  • Benjamin Lecouteux, Pascal Nocéra, Georges Linarès: “Décodage guidé par un modèle cache sémantique”, JEP 2010, Mons, Belgium.
publications.txt · Last modified: 28/02/2013 00:50 by Yannick Estève