Deep Learning for Voice processing
0:00/0:00
From the same archive
From psychoacoustics to deep learning: learning low-level processing of sound with neural networks - Neil Zeghidour
undefined 18 min
Towards helpful, customer-specific Text-To-Speech synthesis - David Guennec
undefined 29 min
Tools for creative AI and noise - Philippe Esling
undefined 20 min
Xtextures - Convolutional neural networks for texture synthesis and cross synthesis - Axel Roebel
undefined 20 min
Round Table IA : Questions/discussions
undefined 30 min
Melodic Scale and Virtual Choir, Max ISiS - Grégory Beller
undefined 26 min
Greg Beller, David Guennec, Nicolas Obin, Axel Roebel, Hugues Vinet. Table ronde
undefined 20 min
Session IA - An overview of AI for Music and Audio Generation - Doug Eck
undefined 47 min
Interaction with musical generative agents - Jérôme Nika
undefined 21 min
Point sur MacIntel et les logiciels du Forum - Carlos Amado Agon, Riccardo Borghesi, Karim Haddad, Nicholas Ellis
undefined 20 min
Nouveautés AudioSculpt 2.7 et SuperVP 2.91 - Xavier Rodet, Alain Lithaud, Niels Bogaards, Axel Roebel
undefined 01 h 07 min
Nouveautes OpenMusic - Gérard Assayag, Jean Bresson, Carlos Amado Agon, Karim Haddad
undefined 59 min
Point sur le Spatialisateur - Olivier Warusfel, Rémy Muller, Terence Caulkins
undefined 12 min
Nouveautés Modalys - Joël Bensoam, Nicholas Ellis, Jean Lochard
undefined 50 min
Mlys - une interface de contrôle de Modalys dans Max/MSP - Manuel Poletti
undefined 47 min
Accueil - Andrew Gerzso
undefined 18 min
Développements récents de l'équipe applications temps réel - Diemo Schwarz, Riccardo Borghesi, Norbert Schnell
undefined 51 min
Deep Neural Networks are increasingly dominating the research activities in the Analysis/Synthesis team and elsewhere. The session will present some of the recent results of the research activities related to voice processing with deep neural networks. The presentation will discuss notably
- Analysis: F0 analysis with convolutional neural networks, Speech/Singing alignment with the CTC loss (ANR project ARS)
- Neural vocoder (ANR projects ARS and theVoice)
- Voice Conversion (ANR project theVoice).
speakers
information
- Type
- Ensemble de conférences, symposium, congrès
- performance location
- Ircam, Salle Igor-Stravinsky (Paris)
- duration
- 32 min