O3 - Oral Session:

Automatic Speech Recognition I

Date: Thursday, 20 November          Location: Building A, Salón de actos.

Hour: 09:00 - 10:40                          Chairperson: Doroteo T. Toledano

  • O3-1: Phoneme-Lattice to Phoneme-Sequence Matching Algorithm based on Dynamic Programming, Ciro Gracia, Xavier Anguera, Jordi Luque and Ittai Artzi.
  • O3-2: Deep Maxout Networks applied to Noise-Robust Speech Recognition, Fernando De la Calle Silos, Ascension Gallardo Antolin and Carmen Peláez Moreno.
  • O3-3: A Deep Neural Network Approach for Missing-Data Mask Estimation on Dual-Microphone Smartphones: Application to Noise-Robust Speech Recognition, Iván López-Espejo, Jose González, Ángel M. Gómez García and Antonio Miguel Peinado Herreros.
  • O3-4: Language Model Adaptation for Lecture Transcription by Document Retrieval, Adrià Martínez-Villaronga, Miguel Angel del Agua, Joan Albert Silvestre-Cerdà, Jesús Andrés-Ferrer and Alfons Juan.
  • O3-5: Articulatory Feature Extraction from Voice and their Impact on Hybrid Acoustic Models, Jorge LLombart, Antonio Miguel and Eduardo Lleida Solano.

Additional information