5 citations · 7 across the 14 of their papers we have counts for
15 papers
LiveBand: Live Accompaniment Generation in the Audio Domain
Marco Pasini, Javier Nistal, Ben Hayes +3
We present LiveBand, a real-time system that generates high-fidelity music accompaniments to live audio input, respecting strict causal constraints. Our method trains a causal tran…
Diffusion Timbre Transfer Via Mutual Information Guided Inpainting
Ching Ho Lee, Javier Nistal, Stefan Lattner +2
We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that…
Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders
Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini +2
We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptually motivated losses, yields encodings that are struc…
CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio
Marco Pasini, Stefan Lattner, George Fazekas
Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continu…
PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
Alain Riou, Bernardo Torres, Ben Hayes +4
In this paper, we introduce PESTO, a self-supervised learning approach for single-pitch estimation using a Siamese architecture. Our model processes individual frames of a Variable…
Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding
Marco Pasini, Stefan Lattner, George Fazekas
Efficiently compressing high-dimensional audio signals into a compact and informative latent space is crucial for various tasks, including generative modeling and music information…
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…
Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates
Marco Pasini, Stefan Lattner, George Fazekas
Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating…
PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective
Alain Riou, Stefan Lattner, Gaëtan Hadjeres +1
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 mo…