32 citations · 187 across the 20 of their papers we have counts for
22 papers
Transfer Learning and Bias Correction with Pre-trained Audio Embeddings
Changhong Wang, Gaël Richard, Brian McFee
Deep neural network models have become the dominant approach to a large variety of tasks within music information retrieval (MIR). These models generally require large amounts of (…
Video-to-Music Recommendation using Temporal Alignment of Segments
Laure Prétet, Gaël Richard, Clément Souchier +1
We study cross-modal recommendation of music tracks to be used as soundtracks for videos. This problem is known as the music supervision task. We build on a self-supervised system…
Exploiting Device and Audio Data to Tag Music with User-Aware Listening Contexts
Karim M. Ibrahim, Elena V. Epure, Geoffroy Peeters +1
As music has become more available especially on music streaming platforms, people have started to have distinct preferences to fit to their varying listening situations, also know…
Unsupervised Music Source Separation Using Differentiable Parametric Source Models
Kilian Schulze-Forster, Gaël Richard, Liam Kelley +2
Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding…
DarkGAN: Exploiting Knowledge Distillation for Comprehensible Audio Synthesis with GANs
Javier Nistal, Stefan Lattner, Gaël Richard
Generative Adversarial Networks (GANs) have achieved excellent audio synthesis quality in the last years. However, making them operable with semantically meaningful controls remain…
Probabilistic semi-nonnegative matrix factorization: a Skellam-based framework
Benoit Fuentes, Gaël Richard
We present a new probabilistic model to address semi-nonnegative matrix factorization (SNMF), called Skellam-SNMF. It is a hierarchical generative model consisting of prior compone…
VQCPC-GAN: Variable-Length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding
Javier Nistal, Cyran Aouameur, Stefan Lattner +1
Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representatio…
Cross-Modal Music-Video Recommendation: A Study of Design Choices
Laure Pretet, Gael Richard, Geoffroy Peeters
In this work, we study music/video cross-modal recommendation, i.e. recommending a music track for a video or vice versa. We rely on a self-supervised learning paradigm to learn fr…
Self-Supervised VQ-VAE for One-Shot Music Style Transfer
Ondřej Cífka, Alexey Ozerov, Umut Şimşekli +1
Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications shortly after its intr…
Comparing Representations for Audio Synthesis Using Generative Adversarial Networks
Javier Nistal, Stefan Lattner, Gaël Richard
In this paper, we compare different audio signal representations, including the raw audio waveform and a variety of time-frequency representations, for the task of audio synthesis…
Learning to rank music tracks using triplet loss
Laure Prétet, Gaël Richard, Geoffroy Peeters
Most music streaming services rely on automatic recommendation algorithms to exploit their large music catalogs. These algorithms aim at retrieving a ranked list of music tracks ba…
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks
Umut Şimşekli, Mert Gürbüzbalaban, Thanh Huy Nguyen +2
The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \emph{classical} central…
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise
Thanh Huy Nguyen, Umut Şimşekli, Mert Gürbüzbalaban +1
Stochastic gradient descent (SGD) has been widely used in machine learning due to its computational efficiency and favorable generalization properties. Recently, it has been empiri…
Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization
Thanh Huy Nguyen, Umut Şimşekli, Gaël Richard
Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical gua…
Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision
Sanjeel Parekh, Alexey Ozerov, Slim Essid +3
We tackle the problem of audiovisual scene analysis for weakly-labeled data. To this end, we build upon our previous audiovisual representation learning framework to perform object…
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
Umut Şimşekli, Çağatay Yıldız, Thanh Huy Nguyen +2
Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence…
Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
Sanjeel Parekh, Slim Essid, Alexey Ozerov +3
Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel…
A Generative Model for Non-Intrusive Load Monitoring in Commercial Buildings
Simon Henriet, Umut Simsekli, Benoit Fuentes +1
In the recent years, there has been an increasing academic and industrial interest for analyzing the electrical consumption of commercial buildings. Whilst having similarities with…
Robust Downbeat Tracking Using an Ensemble of Convolutional Networks
S. Durand, J. P. Bello, B. David +1
In this paper, we present a novel state of the art system for automatic downbeat tracking from music signals. The audio signal is first segmented in frames which are synchronized a…
Stochastic Quasi-Newton Langevin Monte Carlo
Umut Şimşekli, Roland Badeau, A. Taylan Cemgil +1
Recently, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods have been proposed for scaling up Monte Carlo computations to large data problems. Whilst these approaches…
Blind Denoising with Random Greedy Pursuits
Manuel Moussallam, Alexandre Gramfort, Laurent Daudet +1
Denoising methods require some assumptions about the signal of interest and the noise. While most denoising procedures require some knowledge about the noise level, which may be un…
Matching Pursuits with Random Sequential Subdictionaries
Manuel Moussallam, Laurent Daudet, Gaël Richard
Matching pursuits are a class of greedy algorithms commonly used in signal processing, for solving the sparse approximation problem. They rely on an atom selection step that requir…