Guillermo Aradilla

Research Field:

- Automatic Speech Recognition

Research Topics:

- Signal Processing, Machine Learning

Biography

Guillermo Aradilla received the Bachelor's and the M.S. degrees in electrical engineering from the Universitat Politecnica de Catalunya, Spain. He also finished the European Master in Language and Speech. He is currently working as research assistant at IDIAP and is in

his final year of Ph.D.  degree in automatic speech recognition at EPFL, Switzerland. His research is mainly focused on statistical approaches for acoustic models. His main research interests are in the field of signal processing and artificial intelligence, specifically in

pattern recognition and machine learning problems that arise in the computational study of human speech and language.

Email: guillermo.aradilla (a) gmail.com

Publications

• Detección and Recognition of Number Sequences in Spoken

  Utterances, Guillermo Aradilla, and Jitendra Ajmera, in “2nd Workshop on Speech

  in Mobile and Pervasive Environments (SiMPE)”, 2007

• Posterior-based Features and Distances in Template Matching

  for Speech Recognition”, Guillermo Aradilla and Hervé Bourlard, in “4th Joint

  Workshop on Multimodal Interaction and Related Machina Learning Algorithms

  (MLMI)”, 2007

• An Acoustic Model Based on Kullback-Leibler Divergence for

  Posterior Features, Guillermo Aradilla, Jithendra Vepa, and Hervé Bourlard, in

  "IEEE International Conference on Acoustics, Speech, and Signal Processing

  (ICASSP)", 2007

• Using Posterior-Based Features in Template Matching for

  Speech Recognition, Guillermo Aradilla, Jithendra Vepa, and Hervé Bourlard, in

  "International Conference on Spoken Language Processing (ICSLP)",

  2006

• Using Pitch as Prior Knowledge in Template-Based Speech

  Recognition, Guillermo Aradilla, Jithendra Vepa, and Hervé Bourlard, in

  "IEEE International Conference on Acoustics, Speech, and Signal Processing

  (ICASSP)", 2006

• Improving Speech Recognition Using a Data-Driven Approach, Guillermo

  Aradilla, Jithendra Vepa, and Hervé Bourlard, in "Proceedings of

  Interspeech, 2005"

• Using RASTA in task independent TANDEM feature extraction, Guillermo

  Aradilla, John Dines, and Sunil Sivadas, in "International Conference on

  Spoken Language Processing (ICSLP)", 2005