PEOPLE
Carlos Antonio Molina Sánchez
Doctor in Electrical Engineering
 
Research assistant and software developer
 
e-mail cmolina@ing.uchile.cl
   
Education
  • Doctor in Electrical Engineering, University of Chile 2010.
  • Master of Science in Electrical Engineering, University of Chile 2005.
  • Engineer degree in Electrical Engineering, University of Chile 2005.
  • Bachelor of Engineering in Electrical Engineering, University of Chile 2003.
    		•
    Awards
  • CONICYT grant to attend an internship in Signal Analysis and Interpretation Laboratory (SAIL), University of Southern California, 2008.
  • CONICYT scholarship for PhD education in Electrical Engineering at Universidad de Chile, Santiago, Chile, 2006.
  • ISCA grant (International Speech Communication Association) to participate in INTERSPEECH 2004, Jeju Island, Korea. Octubre 4-8.
  • Honor's roll student, top 5 percent, at Electrical Engineering Department, Universidad de Chile, 2002.
    • Research Interests
  • Speech technologies
  • Computer aided pronunciation training
  • Telecommunications
  • Software development
  • Digital signal processing
    		•
     
    Journal Papers
    • Fernando Huenupan, Nestor Becerra Yoma, Claudio Garreton and Carlos Molina. Incremental information based on-line optimization of linear combination of classifiers in speaker verification. ETRI (Electronics and Telecommunications Research Institute) journal, Volume 32, no.3, pp.395-405, 2010.
    • Carlos Molina, Nestor Becerra Yoma, Fernando Huenupán, Claudio Garretón, and Jorge Wuth "Maximum Entropy-Based Reinforcement Learning Using a Confidence Measure in Speech Recognition for Telephone Speech," Audio, Speech, and Language Processing, IEEE Transactions on , vol.18, no.5, pp.1041-1052, July 2010
    • Carlos Molina, Nestor Becerra Yoma, Jorge Wuth and Hiram Vivanco. ASR based pronunciation evaluation with automatically generated competing vocabulary and classifier fusion. Speech Communciation (Elsevier), Volume 51, pag. 485-498, 2009.
    • Fernando Huenupan, Nestor Becerra Yoma, Carlos Molina and Claudio Garreton. Confidence based multiple classifier fusion in speaker verification. Pattern Recognition Letters, Volume 29, Issue 7, 1, Pages 957-966. May 2008 (pdf).
    • Nestor Becerra Yoma, Claudio Garreton, Carlos Molina and Fernando Huenupan. Unsupervised intra-speaker variability compensation based on Gestalt and model adaptation in speaker verification with telephone speech. Speech Communication, In Press, Corrected Proof, Available online 5 December 2007 (pdf).
    • Néstor Becerra Yoma and Carlos Molina. Feature-Dependent Compensation of Coders in Speech Recognition. Signal Processing, Elsevier. Vol. 86, Issue 1, Pages 38-49. January 2006.
    • Néstor Becerra Yoma, Carlos Molina, Jorge Silva and Carlos Busso. Modelling, estimating and compensating low-bit rate coding distortion in speech recognition. IEEE Transactions on Speech and Audio Processing. Vol. 14, Issue 1, Pages 246-255. January 2006.
    • Néstor Becerra Yoma, Jorge Carrasco and Carlos Molina. Bayes-Based Confidence Measure in Speech Recognition. IEEE Signal Processing Letters Vol. 12, Nº11. November 2005.
    Speech Processing and Transmission Laboratory