I received my PhD on talking-face biometric authentication from Telecom ParisTech (France) in 2007.
In 2008, I joined Dublin City University (Ireland) to work on video summarization techniques applied to user-generated content.
I have been a permanent CNRS researcher since 2008:
- at IRIT (Toulouse, France) in the SAMoVA group until 2010
- at LIMSI (Orsay, France) in the Spoken Language Processing group until 2020
- back at IRIT (Toulouse, France) until today
My current research interests include deep learning techniques applied to machine listening, with a strong focus on speaker diarization: I am proud to be known as “the guy behind pyannote”.
Since 2021, I propose (paid) scientific consulting services to companies willing to make the most of their data and open-source speech processing toolkits (and pyannote in particular).
Contact
- Postal Address: IRIT, 118 Route de Narbonne, F-31062 Toulouse, Cedex, France
- Office: IRIT1 219 (2nd floor)
- E-mail: herve.bredin@irit.fr
- Tel: +33 (0)5 61 55 68 86
Curriculum vitae
Work experience
2019-today: Niderb Consulting / Auzeville-Tolosane, France
Scientific consultant. Self-employed. Helping companies make the most of their data and open-source speech processing toolkits (and pyannote in particular)
2020-today: CNRS / IRIT / Toulouse, France
Research scientist. Member of the SAMoVA team. Speaker diarization
2010-2020: CNRS / LIMSI (now LISN) / Orsay, France
Research scientist. Member of the TLP team. Speaker diarization
2008-2010: CNRS / IRIT / Toulouse, France
Research scientist. Member of the SAMoVA team. Content-based video analysis
2008: DCU /Dublin, Ireland
Postdoctoral researcher. Member of the CDVP lab. Automatic summarization of user-generated content
Education
PhD / 2004-2007 / Télécom Paris / Paris, France
MSc / 2001-2004 / Télécom Paris / Paris, France
Signal processing and pattern recognition