imatge

Contents copyright © 2012
La Salle (URL)
All rights reserved


Francesc Alías Pujol

falias@salle.url.edu

idioma/language
  salle_logo

Supervised theses & offers

Ph.D. Theses

  • Topic:"Articulatory synthesis of vowels and syllables using stabilised finite element methods" , Marc Arnela (co-supervised with Dr. Oriol Guasch)

  • Topic:"Natural language processing applied to speech technologies" , Alexandre Trilla (supervisor). Thesis proposal dissertation (ABD): June 8, 2010.

  • Topic:"Environmental sound source recognition" , Xavier Valero (supervisor). Thesis proposal dissertation (ABD): June 8, 2010.

  • Topic:"Perceptual optimization of speech synthesis systems based on unit selection through active interactive genetic algorithms" , Lluís Formiga (supervisor). Thesis proposal dissertation (ABD): December 19, 2007. PhD defense: April 27, 2011. [ppt] [TDX]

  • Title:"Hierarchical self-refining consensus architectures and soft consensus functions for robust multimedia clustering" , Xavier Sevillano (co-supervised with Dr. Joan Claudi Socoró). PhD defense: June 8, 2009

  • Title: "Towards a teaching methodology for presential engineering students based on active learning, compatible with the European Higher Education Area requirements" , José Antonio Montero (co-supervised with Dr. Joan Vicenç Gómez from UPC). PhD defense: February 22, 2008

Master of Science (MSc)

  • "Analysis and modeling of a storyteller: narrative situations and emotions in the characters" , Raúl Montaño Aparicio (November 2011).

  • "Singing voice synthesis from HMM-based speaking voices" , Marc Freixes Guerreiro (November 2011).

  • "A signing speech synthesis system based on HNM with MIDI input" , Ester Cierco Molins (November 2009).

  • "Articulatory synthesis of vowels by means of finite differences" , Marc Arnela Coll (November 2009) (co-supervised with Dr. Oriol Guasch)

  • "Neural Networks for automatic environmental sound source recognition" , Xavier Valero González (March 2009).

  • "Pattern recognition techniques for noise source identification and separation" , Xavier Valero González (February 2009).

  • "ELENA: E-Learning Environment with Natural language-based Assessment" , David García Solórzano (November 2008).

  • "MAGNUS: Mouse Advanced GNU Speech" , Alexandre Trilla Castello (November 2008).(see the demos section)

  • "A comparison between measured and synthesized HRTF's" , Matthias Eibel (October 2008).

  • "Analysis of objective measures for estimating speech discontinuities" , Manuel Pablo Triviño (November 2007).

  • "Emotion identification from text" , David García Solórzano (July 2007).

  • "Fatigue and ambiguity reduction for speech synthesis subjective weight tuning" , Lluís Formiga Fanals (2005).

  • "Text categorization for optimizing text-to-speech synthesis" , Pere Barnola Augé (2004).

Bachelor of Sciencie (BSc)

  • "Design and implementation of a tool for TTS systems speech quality assessment" , Cira Viladegut (under development).

  • "HNM-based voice transformation for synthesizing the Lombard effect" , Eduard Saborit Juberias (Novembre 2010).

  • "Analysis on the use of speech synthesis technology in the media in Catalonia" , Anna Torrens González (Novembre 2010).

  • "Automatic pitch marking system on peaks or valleys" , Natàlia Munné Garcia (November 2009).

  • "Subjective evaluation of acoustic distances based on formants" , Cristina González Lindes (November 2009).

  • "Design and implementation of a tool for teaching speech recognition" , Ester Nieto Bou (November 2009).

  • "Analysis and improvement of a text classifier for multi-domain text-to-speech synthesis" , Isaac Lozano Martín (November 2009).

  • "Analysis of speech corpora oriented to storytelling speech synthesis" , Raúl Montaño Aparicio (November 2009).

  • "Personalized music classification according to emotional feeling" , Lidia San Emeterio (November 2008). [link]

  • "Towards a pocket TTS: reproducing Catalan transcribed speech sounds" , Jaume Torras (December 2007).

  • "Set of tools applied to the teaching of the course entitled Speech Recognition and Synthesis" , Anna Navarro (July 2007).

  • Text-to-speech synthesis for multimedia applications, incorporating text labelling and voice generation tools , David García Solórzano (2005).

  • "Comparative of objective measures for evaluating speech discontinuities in text-to-speech systems" , Manuel Pablo Triviño (July 2004).

  • "Weight tuning for speech synthesis based on interactive genetic algorithms" , Lluís Formiga Fanals (2003) (co-supervised with Dr. Xavier Llorà).

  • "Towards the generation of a new voice in Catalan using the Festival Speech Synthesis System" , Jordi Domínguez Fuster (2003).

  • "Integration of a Catalan text-to-speech system under SAPI 5.1" , Maria Encarnación Navarro (2002).

  • "Interactive tool for teaching speech coding systems" , Josep Creus Navarro (2001).