Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Postolache, Emilian"'
Autor:
Postolache, Emilian, Polouliakh, Natalia, Kitano, Hiroaki, Connelly, Akima, Rodolà, Emanuele, Cosmo, Luca, Akama, Taketo
In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of reconstructing naturalistic music from electroencephalogram (EEG) recordings. Unlike simpler music with limited timbre
Externí odkaz:
http://arxiv.org/abs/2405.09062
Autor:
Ciranni, Ruben, Postolache, Emilian, Mariani, Giorgio, Mancusi, Michele, Cosmo, Luca, Rodolà, Emanuele
We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of stems (or th
Externí odkaz:
http://arxiv.org/abs/2404.16969
Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the joint distr
Externí odkaz:
http://arxiv.org/abs/2403.11706
In recent studies, diffusion models have shown promise as priors for solving audio inverse problems. These models allow us to sample from the posterior distribution of a target signal given an observed signal by manipulating the diffusion process. Ho
Externí odkaz:
http://arxiv.org/abs/2311.07345
Autor:
Comunità, Marco, Gramaccioni, Riccardo F., Postolache, Emilian, Rodolà, Emanuele, Comminiello, Danilo, Reiss, Joshua D.
Sound design involves creatively selecting, recording, and editing sound effects for various media like cinema, video games, and virtual/augmented reality. One of the most time-consuming steps when designing sound is synchronizing audio with video. I
Externí odkaz:
http://arxiv.org/abs/2310.15247
Autor:
Santilli, Andrea, Severino, Silvio, Postolache, Emilian, Maiorca, Valentino, Mancusi, Michele, Marin, Riccardo, Rodolà, Emanuele
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the MT model,
Externí odkaz:
http://arxiv.org/abs/2305.10427
Autor:
Mariani, Giorgio, Tallini, Irene, Postolache, Emilian, Mancusi, Michele, Cosmo, Luca, Rodolà, Emanuele
In this work, we define a diffusion-based generative model capable of both music synthesis and source separation by learning the score of the joint probability density of sources sharing a context. Alongside the classic total inference tasks (i.e., g
Externí odkaz:
http://arxiv.org/abs/2302.02257
Autor:
Postolache, Emilian, Mariani, Giorgio, Mancusi, Michele, Santilli, Andrea, Cosmo, Luca, Rodolà, Emanuele
Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent spaces (e.
Externí odkaz:
http://arxiv.org/abs/2301.08562
Universal sound separation consists of separating mixes with arbitrary sounds of different types, and permutation invariant training (PIT) is used to train source agnostic models that do so. In this work, we complement PIT with adversarial losses but
Externí odkaz:
http://arxiv.org/abs/2210.12108
Autor:
Mancusi, Michele, Postolache, Emilian, Mariani, Giorgio, Fumero, Marco, Santilli, Andrea, Cosmo, Luca, Rodolà, Emanuele
State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are typically hig
Externí odkaz:
http://arxiv.org/abs/2110.05313