Publications
Journal Articles
[1] M. Umbert, J. Bonada, M. Goto, T. Nakano, J. Sundberg, Expression Control in Singing Voice Synthesis: Features, Approaches, Evaluation, and Challenges. IEEE Signal Processing Magazine, 2015. [In Press]
Awards
[1] Winner at the Singing Synthesis Challenge: Fill-in the gap at INTERSPEECH 2016
Conferences
[4] C. Segura, D. Balcells, M. Umbert et al, Automatic speech feature learning for continuous prediction of customer satisfaction in contact center phone calls, Iberspeech, Lisbon, November 2016 [Proceedings]
[3] J. Bonada, M. Umbert, M. Blaauw, Expressive Singing Synthesis Based on Unit Selection for the Singing Synthesis Challenge 2016, Interspeech, San Francisco, USA, September 2016. [PDF] [Sound samples]
[2] M. Umbert, J. Bonada, M. Blaauw, Generating Singing Voice Expression Contours Based on Unit Selection, Stockholm Music Acoustics Conference (SMAC), Stockholm, Sweden, July 2013. [PDF] [poster] [demos]
[1] Pratyush, M. Umbert, X. Serra. A look into the past: Analysis of trends and topics in the Sound & Music Computing Conference. Sound and Music Computing Conference (SMC), Barcelona, Spain. July 2010. [PDF]
[3] J. Bonada, M. Umbert, M. Blaauw, Expressive Singing Synthesis Based on Unit Selection for the Singing Synthesis Challenge 2016, Interspeech, San Francisco, USA, September 2016. [PDF] [Sound samples]
[2] M. Umbert, J. Bonada, M. Blaauw, Generating Singing Voice Expression Contours Based on Unit Selection, Stockholm Music Acoustics Conference (SMAC), Stockholm, Sweden, July 2013. [PDF] [poster] [demos]
[1] Pratyush, M. Umbert, X. Serra. A look into the past: Analysis of trends and topics in the Sound & Music Computing Conference. Sound and Music Computing Conference (SMC), Barcelona, Spain. July 2010. [PDF]
Workshops
[2] M. Umbert, Invited Workshop on the Synthesis of Singing, 40th International Computer Music Conference (ICMC) and the 11th Sound & Music Computing conference (SMC), Athens, Greece, September 2014.
[1] M. Umbert, J. Bonada, M. Blaauw, Systematic Database Creation for Expressive Singing Voice Synthesis Control, 8th ISCA Speech Synthesis Workshop (SSW8), Barcelona, Spain, September 2013. [PDF]
[1] M. Umbert, J. Bonada, M. Blaauw, Systematic Database Creation for Expressive Singing Voice Synthesis Control, 8th ISCA Speech Synthesis Workshop (SSW8), Barcelona, Spain, September 2013. [PDF]
Thesis
[2] M. Umbert. Emotional Speech Synthesis for a Radio DJ: Corpus Design and Expression Modeling. MSc Thesis. Universitat Pompeu Fabra, Barcelona, Spain. September 2010. [PDF]
[1] M. Umbert, Estimation de la fréquence fondamentale du signal de parole (Stage de fin d’études du mastère SCN en collaboration avec France Télécom), ENST-Bretagne, Brest, avril-septembre 2004. [link]
[1] M. Umbert, Estimation de la fréquence fondamentale du signal de parole (Stage de fin d’études du mastère SCN en collaboration avec France Télécom), ENST-Bretagne, Brest, avril-septembre 2004. [link]
Scientific Service
- Conference review: SMAC/SMC 2013, ICMC/SMC 2014
- Conference collaboration committee: SSW8 2013
Research stays
- September 2010 - February 2011 (5 months): Vocaloid team at the YAMAHA Corporate Research and Development Center, Hamamatsu, Japan
- September 2003 - September 2004 (1 year): Erasmus scholarship at the ENST-Bretagne, Brest, France.