Deep Voice, Paris

  • Encounter

  • June 15, through Fri 17 June 2022,
    2 p.m.

  • SCAI et Ircam
    Access plan

  • Presentation, 2 workshops, social event : 450 €
    For students, presentations, 2 workshops, social event : 150 €
    Presentations only: free entry, registration required

    Reserve


Diversity and Inclusion in Vocal Technologies

Deep Voice, Paris is the Parisian event dedicated to voice and artificial intelligence, which aims to bring together scientific and technical expertise, innovation and entrepreneurship. Diversity and inclusiveness will be the focus of this second edition, with discussions on the presence of rare languages, sparsely used languages, sign language, dialects and accents, bias and discrimination in voice technologies.

Hands-on technical workshops will be offered to participants to develop their skills in the fields of speech processing and natural language. Social and networking events at the end of the day will facilitate casual meetings and exchanges among participants.

Speakers Emil Asmussen Q project, Mathieu Avanzi Sorbonne Université, Djenebou Bathily Université Vincennes – Saint-Denis, Mélissa Barkat Defradas Institut des Sciences de l'Evolution, Laurent Besacier GIPSA lab Grenoble, Eric de la Clergerie Inria, Luc Julia Renault, Victoria Khurshudyan INALCO, Anton Lozhkov Hugging Face, Carl Robinson Rumble studio, Djamé Seddah Sorbonne Université, Maxim Serebryakov SANAS, Laure Soulier Sorbonne Université, Agnès Vourc'h CNRHR Robert Laplane

Organization Nicolas Obin Sorbonne Université-STMS, Xavier Fresquet SCAI (Sorbonne Center for Artificial Intelligence, Sorbonne Université)

Program

Wednesday, June 15 (2:00-5:00 pm, location: SCAI)

2:00-2:15 pm at SCAI
Introduction, Nicolas Obin, STMS (IRCAM, Sorbonne University, CNRS, French Ministry of Culture) and Xavier Fresquet, Sorbonne Center for Artificial Intelligence, Sorbonne University

2:15-3:30 pm at SCAI
Keynote "History of voice technologies, current developments and perspectives
Speaker: Luc Julia, Renault
Moderator: Nicolas OBIN, STMS (IRCAM, Sorbonne University, CNRS, French Ministry of Culture)

3:30-5:00 pm at SCAI
Discussion (in English): "What about my voice, what does it have as a gender?"
Abstract: What are the relationships between voice and gender? How does gender interact with identity and emotion? How do we consider gender in voice technologies?
Speakers: Emil Asmussen, Creative Director of Meet Q, The World's First Genderless Voice, Melissa A. Barkat-Defradas, Institute of Evolutionary Science, Nadine Lavan, Queen Mary University of London, Giulia Perugia, Eindhoven University of Technology (TU/e) - Eindhoven (Netherlands)
Moderators: Victor Rosi (IRCAM), Sylvie Saget (University of Gothenburg)

5:00-6:30 pm
Reception at the SCAI, evening meetings and networking

Thursday June 16 (10:00 am-1:00 pm, location: SCAI, then 2:00-5:00 pm, location: IRCAM)

10:00 am-1:00 pm at SCAI
Workshop #1: Hands-on speech-to-text with neural networks
Speakers: Yann Teytaut and Clément Le Moine Veillon, STMS (IRCAM, Sorbonne University, CNRS, French Ministry of Culture)

2:00-3:30 pm at IRCAM
Sign language session + SLAM performance
Participants: Agnès Vourc'h, CNRHR Robert Laplane, Michael Filhol, LIMSI, Djenebou Bathily, Université Vincennes - Saint-Denis

3:30-6:00 pm at IRCAM
Discussion: Diversity of languages in the digital world
Abstract: What representation of minority languages in speech technologies? How can technology help preserve languages and cultures?
Speakers: Laurent Besacier, GIPSA lab, Victoria Khurshudyan, INALCO, Esther Klabbers, ReadSpeaker
Moderators: Nicolas Obin, STMS (IRCAM, Sorbonne University, CNRS, French Ministry of Culture)

Friday June 17 (10:00 am-1:00 pm location: SCAI, then 2:00-5:00 pm, location: IRCAM)

10:00 am-1:00 pm at SCAI
Workshop #2: Hands-on CamemBERT
Speakers: Benjamin Muller, Roman Castagne, Nathan Godey (INRIA)

2:00-3:30 pm at IRCAM
Discussion: Is bias in the text?
Speakers: Eric de la Clergerie, Inria, Djamé Seddah, Sorbonne University, Aurélie Névéol, Paris-Saclay University
Moderator: Laure Soulier, Sorbonne University

3:30-5:00 pm at IRCAM
Panel discussion (in English): Dialectal and accentual diversity in speech technologies
Speakers: Mathieu Avanzi, Sorbonne University, Anton Lozhkov, Hugging Face, Maxim Serebryakov, SANAS
Moderator: Carl Robinson (Rumble studio)

5:00-5:15 pm at IRCAM
Concluding remarks, Nicolas Obin, STMS (IRCAM, Sorbonne University, CNRS, French Ministry of Culture) and Xavier Fresquet, Sorbonne University, SCAI

We use cookie technology to measure our online audience and to allow you to share content on social networks via link buttons. Further information.