| 2015 | Interspeech | The role of prosody and voice quality in text-dependent categories of storytelling across languages. | Ral Montao, Francesc Alas |
| 2012 | CBMI | Audio and video cues for geo-tagging online videos in the absence of metadata. | Xavier Sevillano, Xavier Valero, Francesc Alas |
| 2010 | CEC | Evolutionary process indicators for active IGAs applied to weight tuning in unit selection TTS synthesis. | Llus Formiga, Francesc Alas, Xavier Llor |
| 2009 | Interspeech | Sentiment classification in English from sentence-level annotations of emotions regarding models of affect. | Alexandre Trilla, Francesc Alas |
| 2007 | ECIR | A Hierarchical Consensus Architecture for Robust Document Clustering. | Xavier Sevillano, Germn Cobo, Francesc Alas, Joan Claudi Socor |
| 2007 | ICASSP | Prosody Modelling of Spanish for Expressive Speech Synthesis. | Ignasi Iriondo Sanz, Joan Claudi Socor, Francesc Alas |
| 2007 | IWANN | Extracting User Preferences by GTM for aiGA Weight Tuning in Unit Selection Text-to-Speech Synthesis. | Llus Formiga, Francesc Alas |
| 2007 | IWANN | Assessing Students' Teamwork Performance by Means of Fuzzy Logic. | Jos Antonio Montero, Francesc Alas, Carles Garriga, Llus Vicent, Ignasi Iriondo Sanz |
| 2007 | IWANN | Validation of an Expressive Speech Corpus by Mapping Automatic Classification to Subjective Evaluation. | Ignasi Iriondo Sanz, Santiago Planet, Francesc Alas, Joan Claudi Socor, Elisa Martnez Marroqun |
| 2007 | SIGIR | BordaConsensus: a new consensus function for soft cluster ensembles. | Xavier Sevillano, Francesc Alas, Joan Claudi Socor |
| 2006 | GECCO | Analyzing active interactive genetic algorithms using visual analytics. | Xavier Llor, Kumara Sastry, Francesc Alas, David E. Goldberg, Michael Welge |
| 2006 | ICASSP | Efficient Interactive Weight Tuning For Tts Synthesis: Reducing User Fatigue By Improving User Consistency. | Francesc Alas, Xavier Llor, Llus Formiga, Kumara Sastry, David E. Goldberg |
| 2006 | Interspeech | A pitch marks filtering algorithm based on restricted dynamic programming. | Francesc Alas, Carlos Monzo, Joan Claudi Socor |
| 2006 | Interspeech | Multi-domain text-to-speech synthesis by automatic text classification. | Francesc Alas, Joan Claudi Socor, Xavier Sevillano, Ignasi Iriondo Sanz, Xavier Gonzalvo |
| 2006 | SIGIR | Feature diversity in cluster ensembles for robust document clustering. | Xavier Sevillano, Germn Cobo, Francesc Alas, Joan Claudi Socor |
| 2005 | Interspeech | High quality Spanish restricted-domain TTS oriented to a weather forecast application. | Francesc Alas, Ignasi Iriondo Sanz, Llus Formiga, Xavier Gonzalvo, Carlos Monzo, Xavier Sevillano |
| 2004 | ICASSP | ICA-based hierarchical text classification for multi-domain text-to-speech synthesis. | Xavier Sevillano, Francesc Alas, Joan Claudi Socor |
| 2004 | Interspeech | Perception-guided and phonetic clustering weight tuning based on diphone pairs for unit selection TTS. | Francesc Alas, Xavier Llor, Ignasi Iriondo Sanz, Joan Claudi Socor, Xavier Sevillano, Llus Formiga |
| 2003 | ICIP | Text to visual synthesis with appearance models. | Javier Melenchn, Fernando De la Torre, Ignasi Iriondo Sanz, Francesc Alas, Elisa Martnez, Llus Vicent Safont |
| 2003 | Interspeech | Evolutionary weight tuning based on diphone pairs for unit selection speech synthesis. | Francesc Alas, Xavier Llor |
| 2003 | Interspeech | A hybrid method oriented to concatenative text-to-speech synthesis. | Ignasi Iriondo Sanz, Francesc Alas, Javier Sanchis, Javier Melenchn |