Výsledky vyhledávání - "Bazin, Théis"

Report

Spectrogram Inpainting for Interactive Generation of Instrument Sounds

Autor: Bazin, Théis, Hadjeres, Gaëtan, Esling, Philippe, Malt, Mikhail

Publikováno v: Proceedings of the 1st Joint Conference on AI Music Creativity, 2020 (p. 10). Stockholm, Sweden: AIMC

Modern approaches to sound synthesis using deep neural networks are hard to control, especially when fine-grained conditioning information is not available, hindering their adoption by musicians. In this paper, we cast the generation of individual in

Externí odkaz: http://arxiv.org/abs/2104.07519

Zobrazit plný text záznamu

Report

Ultra-light deep MIR by trimming lottery tickets

Autor: Esling, Philippe, Bazin, Theis, Bitton, Adrien, Carsault, Tristan, Devis, Ninon

Current state-of-the-art results in Music Information Retrieval are largely dominated by deep learning approaches. These provide unprecedented accuracy across all tasks. However, the consistently overlooked downside of these models is their stunningl

Externí odkaz: http://arxiv.org/abs/2007.16187

Zobrazit plný text záznamu

Report

NONOTO: A Model-agnostic Web Interface for Interactive Music Composition by Inpainting

Autor: Bazin, Théis, Hadjeres, Gaëtan

Inpainting-based generative modeling allows for stimulating human-machine interactions by letting users perform stylistically coherent local editions to an object using a statistical model. We present NONOTO, a new interface for interactive music gen

Externí odkaz: http://arxiv.org/abs/1907.10380

Zobrazit plný text záznamu

Deep learning for musical scenario inference and prediction: Application to structured co-improvisation

Autor: Bazin, Théis

Publikováno v: [Internship report] Ircam UMR STMS 9912. 2016

The field of musical scenario inference aims at developing systems and algorithms to automatically extract abstract temporal scenarios in music. We call scenario any underlying symbolic sequence that constitutes a higher-level abstraction of an origi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::199da7e9ade6cf64b83699587ed12e24
https://hal.archives-ouvertes.fr/hal-01388645

Zobrazit plný text záznamu

CONSTRAINED MUSIC GENERATION USING MODEL-CHECKING

Autor: Bazin, Théis, Dubnov, Shlomo

Publikováno v: Actes JIM 2016
Journées d'Informatique Musicale
Journées d'Informatique Musicale, Mar 2016, Albi, France

International audience; Numerous works have tackled the problem of style mod- eling: learn some implicit notion of style from an ensemble of musical sequences and generate new content resembling this set of examples. This paper deals with the additio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c81ce3fff65680610542f5e6ae2146fa
https://hal.archives-ouvertes.fr/hal-03126571/document

Zobrazit plný text záznamu

Flux média tuilés polymorphes: une sémantique opérationnelle en Haskell

Autor: Bazin, Théis, Janin, David

Publikováno v: Actes des Vingt-sixièmes Journées Francophones des Langages Applicatifs (JFLA 2015)
Vingt-sixièmes Journées Francophones des Langages Applicatifs (JFLA 2015)
Vingt-sixièmes Journées Francophones des Langages Applicatifs (JFLA 2015), Jan 2015, Le Val d'Ajol, France
Journées Francophones des Langages Applicatifs (JFLA)
Journées Francophones des Langages Applicatifs (JFLA), Jan 2015, Val d'Ajol, France

National audience; De nombreux outils sont aujourd'hui disponibles pour l'analyse et la production temps réel de flux média temporisés : son, vidéo, animation. Néanmoins, la coordination de ces outils, la synchronisation des flux qu'ils analysen

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::b892ee724cda1c23293ddafae5726590
https://hal.archives-ouvertes.fr/hal-01091736

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání