Zobrazeno 1 - 10
of 176
pro vyhledávání: '"Hadjeres, A."'
In this paper, we tackle the task of musical stem retrieval. Given a musical mix, it consists in retrieving a stem that would fit with it, i.e., that would sound pleasant if played together. To do so, we introduce a new method based on Joint-Embeddin
Externí odkaz:
http://arxiv.org/abs/2411.19806
This paper explores the automated process of determining stem compatibility by identifying audio recordings of single instruments that blend well with a given musical context. To tackle this challenge, we present Stem-JEPA, a novel Joint-Embedding Pr
Externí odkaz:
http://arxiv.org/abs/2408.02514
This paper addresses the problem of self-supervised general-purpose audio representation learning. We explore the use of Joint-Embedding Predictive Architectures (JEPA) for this task, which consists of splitting an input mel-spectrogram into two part
Externí odkaz:
http://arxiv.org/abs/2405.08679
In this paper, we address the problem of pitch estimation using Self Supervised Learning (SSL). The SSL paradigm we use is equivariance to pitch transposition, which enables our model to accurately perform pitch estimation on monophonic audio after b
Externí odkaz:
http://arxiv.org/abs/2309.02265
Autor:
Hadjeres, Gaëtan, Crestel, Léopold
Autoregressive models are now capable of generating high-quality minute-long expressive MIDI piano performances. Even though this progress suggests new tools to assist music composition, we observe that generative algorithms are still not widely used
Externí odkaz:
http://arxiv.org/abs/2107.05944
Autor:
Rouard, Simon, Hadjeres, Gaëtan
In this paper, we propose a novel score-base generative model for unconditional raw audio synthesis. Our proposal builds upon the latest developments on diffusion process modeling with stochastic differential equations, which already demonstrated pro
Externí odkaz:
http://arxiv.org/abs/2106.07431
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
Deep learning has rapidly become the state-of-the-art approach for music generation. However, training a deep model typically requires a large training set, which is often not available for specific musical styles. In this paper, we present augmentat
Externí odkaz:
http://arxiv.org/abs/2006.13331
Autor:
Hadjeres, Gaëtan, Crestel, Léopold
In this work, we propose a flexible method for generating variations of discrete sequences in which tokens can be grouped into basic units, like sentences in a text or bars in music. More precisely, given a template sequence, we aim at producing nove
Externí odkaz:
http://arxiv.org/abs/2004.10120
Autor:
Hadjeres, Gaëtan, Nielsen, Frank
Distances between probability distributions that take into account the geometry of their sample space,like the Wasserstein or the Maximum Mean Discrepancy (MMD) distances have received a lot of attention in machine learning as they can, for instance,
Externí odkaz:
http://arxiv.org/abs/2002.08345