About
CIRMMT welcomes Moment Factory for a unique workshop combining members of their teams and members of CIRMMT!
The workshop will take place at CIRMMT and will start with a presentation of Moment Factory technologies, projects, problematics and working methods, followed by short presentation (5min) and/or demos by CIRMMT members. The afternoon will end with a 5à7.
The goal of this event is to launch discussions on current and potential future projects: your participation is essential!
Topics
The workshop will touch upon the following topics:
- Audio to Data: Audio Descriptors / Machine Learning
- Data to Audio: Concatenate Synthesis; Database Connectivity for Generative Audio; Sensor Data for Generative Audio
- Movement to Audio: Tactile Interfaces; Skeleton Tracking; Gesture Recognition
- Interactive Audio Devices: Connected / Embedded Devices
- Text to Speech / Speech to Text: AI / Machine Learning
- Immersion: Wave Field Synthesis; Interactive Object Based Audio; Improved Audio Mix Deployment Techniques
- Tools/Previsualisation: Unreal/Unity Spatialised Audio Previsualisation (Binaural); Room Acoustic Simulation (Wave Physics Simulations); Loudspeaker Acoustic Simulation; Spatial Audio Decoding from Game Engine Acoustic Simulations; Live Multichannel Audio for Game Engines (Inputs/Outputs)
- AR/VR
Schedule
13:00 - 15:30 – Presentations in room A-832
·13:00 Paul Chinnery, Moment Factory
13:45 Q/A period
·14:00 Jeremy Cooperstock: AI Digital Nurse Avatar (ADiNA)
Text to Speech / Speech to Text: AI / Machine Learning
·14:05 Dominic Thibault: Machine learning and machine listening tools Mosaïque, Qualia and Neural Audio Synth (multiple projects of Laboratoire formes • ondes)
Audio to Data: Audio Descriptors / Machine Learning;
Data to Audio: Concatenate Synthesis;
Database Connectivity for Generative Audio;
Sensor Data for Generative Audio
·14:15 Miriam Boutros: The ear: a portal to human health
Audio to data
14:20 Q/A period
·14:25 Christophe Lengelé: Live 4 Life: an open-source spatial performance tool
Immersion: Wave Field Synthesis; Interactive Object Based Audio;
Improved Audio Mix Deployment Techniques;
Interactive Audio Devices: Connected / Embedded Devices
·14:30 Pierre Grandjean: Immersive Audio Research at CRASH-UdeS (multiple projects overview)
Interactive Audio Devices: Connected / Embedded Devices
·14:40 Philippe-Aubert Gauthier: Sound Environments, Sound Spaces: Towards New Challenges
Immersion: Wave Field Synthesis; Interactive Object Based Audio; Improved Audio Mix Deployment Techniques
14:45 Q/A period
·14:55 Vincent Cusson: Rapid prototyping for instrument design (presentation on various ongoing projects at IDMIL)
Movement to Audio: Tactile Interfaces; Skeleton Tracking; Gesture Recognition;
Interactive Audio Devices: Connected / Embedded Devices
·15:05 Takuto Fukuda: Mixed Reality (MR) opera on schizophrenia for a singer, small ensemble and MR technologies
Movement to Audio: Tactile Interfaces; Skeleton Tracking; Gesture Recognition; AR/VR
·15:10 Ziyue Piao and Theodora Nestorova: SenSing: Transmitting Kinesthetic Breathing Experiences for Voice Pedagogy & Performance
Movement to Audio: Tactile Interfaces; Skeleton Tracking; Gesture Recognition;
Interactive Audio Devices: Connected / Embedded Devices
·15:15 Rachel Bouserhal/Jérémie Voix: CRITIAS Auditory Research Platform (ARP) and “InteracSon” demonstration
Interactive Audio Devices: Connected / Embedded Devices;
Immersion: Wave Field Synthesis; Interactive Object Based Audio;
Improved Audio Mix Deployment Techniques
15:20 – Q/A period
15:30-16:00 Coffee break (room A-832)
16:00-17:00: Demos in CIRMMT labs (8th floor)
·Edu Meneses & David Ledoux: AudioDice, room 820
Immersion; Spatialization; Loudspeaker acoustic simulation
·Bavo Van Kerrebroeck: Searching Borders, room 821
AR/VR;Audio to Data: Audio Descriptors / Machine Learning
·Gianluca Grazioli: ArcheoEchi, room 822
AR/VR
·Pauline Patie: Immersive Real-Time Control: Custom Audiovisual System for Dome Spatialization, Autoreactivity, and Projection, room 817
Interactive Audio Devices: Connected / Embedded Devices; Movement to Audio: Tactile Interfaces; Skeleton Tracking; Gesture Recognition
·Sarah Hashemi: Singers and pTMD, room 818
MoCap
17:00-18:00 5à7 (room A-832)
Registration
This workshop is open for CIRMMT members only.