undefined 04 min

undefined 14 min

undefined 29 min

undefined 39 min

Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental limita

undefined 18 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 neur

undefined 32 min

The subject of automatic speech synthesis began to be popularised as early as the 1990s. Each of us has already had to deal with automatic answering machine voices that made us all suffer in the beginning. Today, however, the progress made

undefined 29 min

We will present the latest creative tools developed by the RepMus team (ACIDS project), enabling real-time audio synthesis as well as music generation and production and synthesizer control, all in open-source code, as well as Max4Live and

undefined 20 min

Neural style transfer applied to images has received considerable interest and has triggered many research activities aiming to use the underlying strategies for manipulation of music or sound. While the many fundamental differences between

undefined 20 min

undefined 30 min

Dans cette présentation, Greg Beller exposera les développements récents dans le domaine du traitement de la voix. Melodic Scale est un dispositif Max For Live qui modifie automatiquement une ligne mélodique en temps réel, en changeant sa g

undefined 26 min

undefined 20 min

An overview of AI for Music and Audio Generation I'll discuss recent advances in AI for music creation, focusing on Machine Learning (ML) and Human-Computer Interaction (HCI) coming from our Magenta project (g.co/magenta). I'll argue tha

undefined 47 min

The Musical Representations team explores the paradigm of computational creativity using devices inspired by artificial intelligence, particularly in the sense of new symbolic musician-machine interactions. The presentation will focus in pa

undefined 21 min

This demonstration gives an overview of recent developments in the standalone corpus-based concatenative sound synthesis program AudioGuide. New features and methods include revamped hierarchal sound segment matching routines and polyphonic

undefined 44 min

Patching With Complex Data I will show some recent experiments using the Max dictionary in a variety of scenarios related to generative sequencing. Since a patcher itself is in the form of a dictionary, we can also capture and manipulate t

undefined 30 min

My musical collaboration with percussionist Irwin took an unplanned turn when we started working remotely. Over the past year we've developed a workflow that allows us to perform together in real time using instruments that I write in Pure

undefined 27 min

undefined 58 min

undefined 31 min

undefined 41 min

OMChroma new tutorials and documentation. This presentation will focus on my new set of tutorial patches, videos and documentation of the OpenMusic library OM-Chroma. After a five-years teaching experience at the HMDK Stuttgart, I collecte

undefined 21 min

undefined 19 min

The SkataRT environment is built at the intersection of a research and development work on concatenative corpus-based sound synthesis (CataRT) and a European research project on the issue of voice imitation as a tool for sketching and rapid

undefined 28 min

This presentation introduces two software developments, TS2 and Analyse, heirs of the tools offered by the AudioSculpt environment. The IRCAM Lab. TS2 is a sound processing software developed within IRCAM's IMR department. Built around the

undefined 28 min

undefined 26 min

undefined 31 min

undefined 33 min

In this session, we will present the software developments made in 2020 around Spat (for Max) and Panoramix (standalone). These developments concern the addition of new functionalities (notably for the manipulation and decoding of Ambisonic

undefined 28 min

During the past decade, new object-based immersive audio content formats and creation tools were developed for cinematic and musical production. These technologies free the music creator from the constraints of normalized loudspeaker confi

undefined 47 min

undefined 26 min

During this session, 5 new devices distributed by the Forum will be introduced: MarblesLFO and PendulumsLFO use the physical function of Max to emulate two physical systems (marbles falling in a box and a double pendulum) and transform thei

undefined 13 min

SpeaK is a sound lexicon that offers definitions of main sound properties. Each term of the lexicon is illustrated by sound examples that have been created or recorded on purpose, in order to highlight the given property. The tool is embedd

undefined 18 min