5 citations · 7 across the 14 of their papers we have counts for
7 papers · 1 filter
Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation
Marco Pasini, Javier Nistal, Stefan Lattner +1
Autoregressive models are typically applied to sequences of discrete tokens, but recent research indicates that generating sequences of continuous embeddings in an autoregressive m…
Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures
Alain Riou, Antonin Gagneré, Gaëtan Hadjeres +2
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…
Improving Musical Accompaniment Co-creation via Diffusion Transformers
Javier Nistal, Marco Pasini, Stefan Lattner
Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference spe…
Music2Latent: Consistency Autoencoders for Latent Audio Compression
Marco Pasini, Stefan Lattner, George Fazekas
Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existi…
Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation
Alain Riou, Stefan Lattner, Gaëtan Hadjeres +2
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 t…
The evolution of inharmonicity and noisiness in contemporary popular music
Emmanuel Deruty, David Meredith, Stefan Lattner
Much of Western classical music relies on instruments based on acoustic resonance, which produce harmonic or quasi-harmonic sounds. In contrast, since the mid-twentieth century, po…
Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning
Alain Riou, Stefan Lattner, Gaëtan Hadjeres +1
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 ta…