Text-Independent Phone-to-Audio Alignment Leveraging SSL (TIPAA-SSL) Pre-Trained Model Latent Representation and Knowledge Transfer

Noé Tits obtained his Master of Electrical Engineering, specializing in signals, systems and bio-engineering (Magna Cum Laude every year) in June 2017. His master’s thesis was carried out in the context of an Erasmus Plus scholarship at the University of the Basque Country in Bilbao (Spain) in the Aholab laboratory, specializing in speech processing. He developed a tool for analyzing pathological voices. In December 2017, Noé obtained a grant from the FNRS to pursue a PhD at the Numediart Institute of UMONS, ISIA Lab. His PhD thesis was focused on the application of deep learning techniques for controlling the emotional expressiveness in text-to-speech synthesis. He took part in the Research and Development of Flowchase’s speech technology to automatically analyze and provide feedback to English learners using machine/deep learning and signal processing paradigms. The developed speech technology presents cutting-edge deep learning models for phonetic alignment and classification, facilitating multilingual text phonetization and precise speech alignment. Its efficient model training allows for speech-to-text inference, stress intensity analysis, and nuanced intonation assessment, catering to a wide range of industry applications in speech and language processing. Noé Tits is currently working at CluePoints on clinical data analysis, specifically on developing machine learning models and language models to detect clinical data inconsistencies.

Thierry Dutoit graduated as an Electrical Engineer and a PhD in 1988 and 1993 from the Faculté Polytechnique de Mons (now UMONS), Belgium, where he teaches circuit theory, signal processing, and speech processing. In 1995, he initiated the MBROLA project for free multilingual text-to-speech synthesis (TTS). Between 1996 and 1998, he spent 16 months at AT&T-Bell Labs, in Murray Hill (NJ) and Florham Park (NJ). He is the Author of several books on TTS and applied signal processing, and he (co-)wrote more than 20 journal papers, and more than 120 papers on speech processing, biomedical signal processing, and digital art technology. He has been an Associate Editor of the IEEE Trans. on speech and audio processing (2003–2006) and the President of ISCA’s SynSIG interest group on TTS from 2007 to 2010. In 2005, he initiated the eNTERFACE 4-week summer workshops on multimodal interfaces and was the Organizer eNTERFACE'05 in Mons, Belgium. He was also part of the organizing committee of INTERSPEECH'07 in Antwerpen. He is a member of the IEEE Signal Processing and Biomedical Engineering society, and has been part of the Speech and Language Technical Committee of the IEEE since 2009. He successively (co-)founded ACAPELA-GROUP in 1996, a European company specialized in TTS products, the NUMEDIART Institute for Creative Technology in 2009, the FABLAB MONS non-profit-making organization in 2014, the CLICK Living lab in 2016, and the TRAIL inter-university Institute for Trusted AI in 2020.