François Pachet

François Pachet

François Pachet
Born (1964-01-10) January 10, 1964
France, Sainte-Adresse
Residence Paris
Nationality French
Institutions Sony CSL-Paris, 6rue Amyot, 75006 Paris
Patrons Sony CSL
Education Pierre and Marie Curie University
Known for Continuator, Flow Machines
Influenced Artificial intelligence, Music, Audio
Notable awards ECCAI in 2014, best paper award in 2002: The Continuator: Musical Interaction with Style

François Pachet (born 10 January 1964) is a French scientist, director of the Sony Computer Science Laboratory in Paris since 2014. He is one of the pioneers of computer music closely linked to artificial intelligence, especially in the field of machine improvisation and style modelling. He has been elected ECCAI[1] Fellow in 2014.

Education

Pachet received his French Baccalaureate in 1981, at Lycée Montaigne in Paris. In 1981 he started Math Sup/ Math Spé 2-years formation at Lycée Turgot and Lycée Janson de Sailly and was accepted at École des ponts ParisTech from which he graduated in Civil Engineering, and Computer Science in 1987, majoring Applied Mathematics. A year after he went to Kuala Lumpur in the University of Malaya to be a professor. Then from 1992 to 1993 he attended Pierre and Marie Curie University where he got a Master (DEA) in Artificial Intelligence, his music teacher was David Wessel (University of California, Berkeley); and a PhD[2] in Computer Science, (His thesis was "Knowledge representation with objects and rules: the neopuss system", he was supervised by J-F.Perrot). He moved to Montréal for a year to study a Post-doc at Université du Québec à Montréal, graduated in Artificial Intelligence. In 1997, he got his research Advisor Diploma on the thesis subject: "Object-oriented languages and knowledge representation" at University Pierre et Marie Curie. During the 58th national session of Institut des Hautes Etudes en Défense Nationale,[3] in 2006 he was appointed Auditor by the French Prime Minister Dominique de Villepin, and Colonel since September 2007 in the "réserve citoyenne" (french Air Force).

Experiences

His first professional experience was in 1987 in Kuala-Lumpur (Malaysia), during his military service, for a year. When he came back to France, he spent two years working for Pierre et Marie Curie University, first as Monitor, (teaching assistant), then as temporary research assistant. In 1992 Pachet left Paris to work at Université du Québec à Montréal for post-doctoral research on the Cyc project [4] Common sense representation, Douglas Lenat, MCC), with the help of Hafedh Mili professor at UQAM. At the same time, Pachet was a consultant with OTI (Object Technology International, now purchased by IBM), on rule-based systems. In 1993, he returned to Paris to be Assistant Professor (in French, "Maitre de conférence"), at Pierre and Marie Curie University until 1997 (4 years) in Computer Science, Research and Teaching. The first time Pachet worked for SONY-CSL (Computer Science Laboratory) was in 1997 in Paris. He started as a Researcher and at the same time Creator and Manager of a ten person music team. The team's target was to create a unique music content management and interaction technologies. Moreover, 15 patents written and co-written by the scientist about electronic music distribution, audio feature extraction and music interaction were filed by Sony Corporation (EU and USA). In 2005, he was promoted Senior Researcher at SONY-CSL after more than 80 publications in journals[5] and international conferences in the domains of Music, Audio, and Artificial Intelligence. Which then permitted him to become Deputy Director in 2013 and finally Director of Sony Computer Science Laboratories in 2014. The CSL (the branch of Sony-CSL Tokyo) is dedicated to basis research in computer science; it was created by Luc Steels and Mario Tokoro in 1996.

Achievements

The Music team at Sony Computer Science Laboratory Paris was released in 1997 by Pachet, where he developed the vision that metadata can greatly enhance the musical experience, from listening to performance.[6] The FlowComposer[7] is his second achievement, a system to compose lead sheets in the style of arbitrary composers. It was followed by LSDB, the first collecting lead sheets in electronic format with a large-scale effort (Over 11,000 lead sheets collected); and Virtuoso, a solo jazz detector. The “Popular Music Browser” project,[8] which started in 1998, at Sony Computer Science Laboratories This research project covers all areas of the music‐to‐listener chain, from music description, descriptor extraction from the music signal, or data mining techniques, Similarity‐based access, and novel music retrieval methods such as automatic sequence generation, and to user interface issues. Moreover, he has designed the Continuator,[9] a system allowing real-time musical improvisation with an algorithm.[10] He is now the beneficiary of the ERC Grant Flow Machines [11] for investigating how machines can boost creativity in humans and be able to continue a work in the same musical style. Pachet wants a future in which consumers could buy the unique style of an artist and apply it to their own material; he says, "I call it 'Stylistic Cryogenics' -- to freeze the style into an object that can be reused and made alive again".[12] The MusicSpace [13] is a spatialization control system created with O. Delerue in 2000. Another achievement is CUIDADO (Content-based Unified Interfaces and Descriptors for Audio/music Databases available Online),[14] a two year project ended in 2003, on developing content-based,[15] audio modules and applications; the project includes the analysis, the navigation and creative process.This project is satisfying the needs of record labels and copyright societies for Information management methods, for marketing and for protecting their informations, using an Authoring system using content features for professional musicians and studios. Moreover in 2014, Pachet presented two music tutorials on Brazilian guitar and Jazz. His most notable achievement is the Continuator,[16] an interactive music improvisation system.[17] Experimented with many professional musicians, presented notably at the SIGGRAPH’03 conference and considered a reference in the domain of music interaction, an example of a Musical Turing test with the Continuator on VPRO Channel with Jazz Pianist jazz Albert van Veenendaal (Amsterdam).[18] ARTE presents Pachet on Square Idée[19] "Demain, devenir Wagner ou Daft Punk?", (Tomorrow, become Wagner or Daft Punk?) October 2015. Pachet writes about using CP techniques to model style in music and text for ACP (Association for Constraints Programming), in September 2015.

See also

Bibliography

References

  1. "ECCAI Fellows 2014". ECCAI. 2014.
  2. "Francois Pachet Bio". Pachet. 2015.
  3. "Institut des Hautes Etudes de Defence Nationale".
  4. "Cyc project". B.J. Copeland. 2002.
  5. "Language and Brain: What is Up? What is ComingUp?". Journal of Clinical and Experimental Neuropsychology. 2001.
  6. "Pachet". LSE 2014.
  7. "FlowComposer for Leadsheet Generation". Flow Machine. Pachet, F. and Roy, P. Generation of Stylistically Imitative Leadsheets with User Constraints. 2014.
  8. Journal of the American Society for Information Science and Technology (2014). "Popular music access: The Sony music browser". UCL.
  9. "Continuator". François Pachet. 2002.
  10. "Comment copier le style des musiciens". Sylvain Guilbaud. 2015.
  11. "Flow Machines, Can computers can make us more creative?". François Pachet. 2015.
  12. "Musical Flow". Condé Nast UK. 2015.
  13. Pachet.F and O. Delerue (2000). "MusicSpace goes Audio". citeseerx.
  14. "The CUIDADO Project" (PDF). Hugues Vinet IRCAM.
  15. "Cuidado". Ircam. 2003.
  16. "The Continuator: Musical Interaction With Style" (PDF). Journal of New Music Research. 2002.
  17. "FlowMachine le logiciel qui fera de vous un Bob Dylan". 01net. 2014.
  18. "Musical test continuator". Youtube. 2012.
  19. "Square Idée, Demain, devenir Wagner ou Daft Punk?". ARTE 2015.

External links

This article is issued from Wikipedia - version of the 10/1/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.