Academic researcher

Deep learning for audio, speech and natural language processing

Publications: HAL or Google Scholar

Scientific consultant

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).

Open source developer

Reproducible research advocate

  • Lead developer of GitHub stars a deep learning toolkit for speaker diarization
  • Lead developer of GitHub stars face detection, tracking and clustering in videos
  • Lead developer of pyannote.metrics GitHub stars a toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systems

All projects: Github