ゲスト講演:「クリエイティブ・エージェントとのシンボリック・インタラクション」IRCAM ジェラール・アサヤグ(Gerard Assayag)

IRCAMのジェラール・アサヤグ(Gerard Assayag)のゲスト講演が4月10日に行われます。


タイトル: クリエイティブ・エージェントとのシンボリック・インタラクション
日時: 2018年4月10日、18時より
場所: 場所: 東京芸術大学 音楽環境創造科
千住キャンパス、第1講義室
〒120-0034
東京都足立区千住1-25-1
http://www.geidai.ac.jp/access/senju

お問い合わせ: Tel: 050-5525-2742
Email: mce-office@ml.geidai.ac.jp

*講義は日本語訳されます。

IRCAMのGerard Assayagが率いるミュージック・レプレゼンテーション・チームが開発した、 OpenMusic(作曲のためのビジュアル・プログラミング言語)そしてOMax(インタラクティブな人工即興演奏家)をもとに講演が行われます。
https://ja.wikipedia.org/wiki/OpenMusic
http://repmus.ircam.fr/omax/home
概要と略歴は以下を参照してください。

 


Abstract

Symbolic Interaction with Creative Agents

Gerard Assayag
IRCAM (Institut de recherche et de coordination acoustique / musique), Paris

The Music Representation Team originated at IRCAM by Gerard Assayag has issued several software environments that have become internationally renowned among contemporary music creators, such as OpenMusic, a visual programming language for composition, or OMax, an interactive artificial improviser. Gerard Assayag has eventually defined with his team the concept of symbolic interaction in order to account for a rich and versatile musical dialog between machines and human, spanning over several levels of information from acoustics signal to the higher symbolic integration frame skilled musicians are used to.
In order to foster realistic and artistically interesting behaviors of digital interactive systems, and communicate with them in a humanized way, we show how to bring into synergy a combination of means: machine listening — extracting high level features from the signal and turning them into significant symbolic units ; AI and interactive machine learning — discovering and assimilating on the fly intelligent schemes by listening to actual performers ; stylistic simulation— elaborating a consistent model of style ; symbolic music representation — formalized representations connected to organized musical thinking, analysis and composition. All these means cooperate in order to elaborate a multi-dimensional and multi-scale memory model underlying a discovery and learning process, thus contributing to the emergence of creative musical agents.
Creative Symbolic Interaction brings indeed together both the advantages one can get from the worlds of real-time signal computing, and from intelligent, content-level analysis and processing, in order to enhance and humanize man-machine communication.
Performers improvising along with Symbolic Interaction systems experiment a unique artistic situation where they interact with a musical agent which develops itself in its own ways while keeping in style with the user. It aims at defining a new artificial creativity paradigm in computer music, and extends to other fields as well : The idea to bring together composition and improvisation through modeling cognitive structures and processes is a general idea that makes sense in many artistic and non-artistic domains. It corresponds to a decision-making paradigm where a possible strategy consists in weaving decisions step after step, by relating to an overall structural determinism, by listening closely to oneself or to the external environment, or by jumping in an “improvized” way and generate surprises. This kind of “improvisation” strategy is observed in the living world, and might be one aspect of intelligence as a way to cope effectively with the unknow ; it may well serve as a productive model for artificial music creativity.

 

Bio

Gerard Assayag has been until recently head of IRCAM Research Lab, the STMS (Sciences and Technologies of Music and Sound) Lab, and he is currently head of the IRCAM Music Representation Team that he has founded in 1992.
His research interests are centered on music representation issues, including programming language, machine learning, constraint and visual programming, computational musicology, music modeling, and computer-assisted composition. He has designed with his collaborators OpenMusic and OMax, two powerful music research software environments which have gained international reputation and are used in many places around the world for computer assisted composition, analysis and improvisation.
Gérard Assayag is a founding member of AFIM (Association Francaise d’Informatique Musicale) and SMCM (Society for Mathematics and Computation in Music). He serves in the Editorial Boards of Journal of Mathematics and of the Journal of New Music Research (JNMR). He has organized or co-organised the “Forum Diderot, Mathematique et Musique” for the European Mathematical Society in 1999 as well as several international computer music conferences, including the Sound and Music Computing 2004 conference, the 3rd Mathematics and Computation in Music conference in 2011 and the Improtech Paris – New York 2012 and ImproTech Paris-Philadelphia 2017 conference on Improvisation an new technologies, the Mathemusical Conversation Intl Workshop in Singapour in 2015.
Gerard Assayag has been co-editor of several journal special issues on music science such as JNMR or Soft Computing, and of books including «Mathematic and Music » (Springer-Verlag 1999), «The OM Composer’s Book I, II & III» (Delatour 2008-2016), «New Computational Paradigms for Computer Music » (Delatour 2009), «Constraint Programming in Music » (Wiley 2012), « Mathemusical Conversations » (World Scientific 2016).