I'm a researcher at the Center for Translational Neurophysiology of Speech and Communication at the Italian Institute of Technology (IIT). I received a PhD in Computer Science from the Centre for Speech Technology Research at the University of Edinburgh (2006-2010). Before moving to Edinburgh I worked as software engineer/ project manager at Loquendo, a speech technology company (2001-2006). I received a 5-year degree (BEng + MEng) in Electronic Engineering from the Universita’ di Genova (1994-2000).
My research interests include text-to-speech (TTS) synthesis, automatic speech recognition (ASR) with a focus on neuro-inspired ASR, machine learning for speech and language processing, and analysis of non-verbal communication.
Since I joined IIT I have been working on the use of speech production information for ASR. I collaborate with the neuroscientists of my lab (Mirror Neurons and Interaction Lab) to 1) investigate the role of the motor cortex in speech perception through neurophysiological and behavioral experiments and 2) try to build acoustic models that take into account the contribution of motor information.
In IIT I also work on the analysis of non-verbal communication (i.e., sensory-motor communication).
During my PhD I worked on the identification and generation of prosodic prominence patterns for English TTS synthesis with a particular focus on the mechanisms by which context (i.e., discourse and "sentence" context) affects prosodic prominence and on the automatic detection of discourse-context related factors (e.g. focus, contrast) from text.
For code please have a look at the publication section or at https://github.com/robotology/natural-speech .
2010-2013 SIEMPRE - EU 7 Framework Programme ICT - FET
2012-2015 POETICON++ - EU 7 Framework Programme ICT - STREP
2015-2018 ECOMODE - H2020-ICT-2014-1
2016-2017 ALLSpeak (funded by ARISLA)