no code implementations • 20 Feb 2024 • Manvi Agarwal, Changhong Wang, Gaël Richard
Music generated by deep learning methods often suffers from a lack of coherence and long-term organization.
1 code implementation • International Society of Music Information Retrieval 2023 • Bernardo Torres, Stefan Lattner, Gaël Richard
Significant strides have been made in creating voice identity representations using speech data.
1 code implementation • 22 Dec 2023 • Bernardo Torres, Geoffroy Peeters, Gaël Richard
In neural audio signal processing, pitch conditioning has been used to enhance the performance of synthesizers.
1 code implementation • NeurIPS 2023 • Victor Letzelter, Mathieu Fontaine, Mickaël Chen, Patrick Pérez, Slim Essid, Gaël Richard
Multiple Choice Learning is a simple framework to tackle multimodal density estimation, using the Winner-Takes-All (WTA) loss for a set of hypotheses.
1 code implementation • 20 Jul 2023 • Changhong Wang, Gaël Richard, Brian McFee
This approach allows representations derived for one task to be applied to another, and can result in high accuracy with less stringent training data requirements for the downstream task.
no code implementations • 12 Jun 2023 • Laure Prétet, Gaël Richard, Clément Souchier, Geoffroy Peeters
We propose a novel approach to significantly improve the system's performance using structure-aware recommendation.
no code implementations • 11 May 2023 • Jayneel Parekh, Sanjeel Parekh, Pavlo Mozharovskyi, Gaël Richard, Florence d'Alché-Buc
This paper tackles two major problem settings for interpretability of audio processing networks, post-hoc and by-design interpretation.
1 code implementation • 14 Nov 2022 • Karim M. Ibrahim, Elena V. Epure, Geoffroy Peeters, Gaël Richard
Namely, we propose a system which can generate a situational playlist for a user at a certain time 1) by leveraging user-aware music autotaggers, and 2) by automatically inferring the user's situation from stream data (e. g. device, network) and user's general profile information (e. g. age).
no code implementations • 4 Mar 2022 • Milad Sefidgaran, Amin Gohari, Gaël Richard, Umut Şimşekli
Understanding generalization in modern machine learning settings has been one of the major challenges in statistical learning theory.
1 code implementation • 23 Feb 2022 • Jayneel Parekh, Sanjeel Parekh, Pavlo Mozharovskyi, Florence d'Alché-Buc, Gaël Richard
This paper tackles post-hoc interpretability for audio processing networks.
2 code implementations • 24 Jan 2022 • Kilian Schulze-Forster, Gaël Richard, Liam Kelley, Clement S. J. Doire, Roland Badeau
Integrating domain knowledge in the form of source models into a data-driven method leads to high data efficiency: the proposed approach achieves good separation quality even when trained on less than three minutes of audio.
1 code implementation • 7 Jul 2021 • Benoit Fuentes, Gaël Richard
We present a new probabilistic model to address semi-nonnegative matrix factorization (SNMF), called Skellam-SNMF.
1 code implementation • NeurIPS 2021 • Melih Barsbey, Milad Sefidgaran, Murat A. Erdogdu, Gaël Richard, Umut Şimşekli
Neural network compression techniques have become increasingly popular as they can drastically reduce the storage and computation requirements for very large networks.
1 code implementation • 18 May 2021 • Antoine Liutkus, Ondřej Cífka, Shih-Lun Wu, Umut Şimşekli, Yi-Hsuan Yang, Gaël Richard
Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity.
1 code implementation • 4 May 2021 • Javier Nistal, Cyran Aouameur, Stefan Lattner, Gaël Richard
Influenced by the field of Computer Vision, Generative Adversarial Networks (GANs) are often adopted for the audio domain using fixed-size two-dimensional spectrogram representations as the "image data".
1 code implementation • 10 Feb 2021 • Ondřej Cífka, Alexey Ozerov, Umut Şimşekli, Gaël Richard
While several style conversion methods tailored to musical signals have been proposed, most lack the 'one-shot' capability of classical image style transfer algorithms.
1 code implementation • IEEE/ACM Transactions on Audio, Speech, and Language Processing 2020 • Ondřej Cífka, Umut Şimşekli, Gaël Richard
Style transfer is the process of changing the style of an image, video, audio clip or musical piece so as to match the style of a given example.
no code implementations • 18 May 2020 • Laure Prétet, Gaël Richard, Geoffroy Peeters
These algorithms aim at retrieving a ranked list of music tracks based on their similarity with a target music track.
no code implementations • 29 Nov 2019 • Umut Şimşekli, Mert Gürbüzbalaban, Thanh Huy Nguyen, Gaël Richard, Levent Sagun
This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochastic differential equation (SDE) driven by a Brownian motion.
1 code implementation • 4 Jul 2019 • Ondřej Cífka, Umut Şimşekli, Gaël Richard
Research on style transfer and domain translation has clearly demonstrated the ability of deep learning-based algorithms to manipulate images in terms of artistic style.
1 code implementation • NeurIPS 2019 • Thanh Huy Nguyen, Umut Şimşekli, Mert Gürbüzbalaban, Gaël Richard
We show that the behaviors of the two systems are indeed similar for small step-sizes and we identify how the error depends on the algorithm and problem parameters.
no code implementations • 22 Jan 2019 • 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 guarantees have been proven for both asymptotic and finite-time regimes.
no code implementations • 9 Nov 2018 • Sanjeel Parekh, Alexey Ozerov, Slim Essid, Ngoc Duong, Patrick Pérez, Gaël Richard
We tackle the problem of audiovisual scene analysis for weakly-labeled data.
no code implementations • ICML 2018 • Umut Şimşekli, Çağatay Yıldız, Thanh Huy Nguyen, Gaël Richard, A. Taylan Cemgil
The results support our theory and show that the proposed algorithm provides a significant speedup over the recently proposed synchronous distributed L-BFGS algorithm.
no code implementations • 19 Apr 2018 • Sanjeel Parekh, Slim Essid, Alexey Ozerov, Ngoc Q. K. Duong, Patrick Pérez, Gaël Richard
Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events.
no code implementations • NeurIPS 2016 • Alain Durmus, Umut Simsekli, Eric Moulines, Roland Badeau, Gaël Richard
We illustrate our framework on the popular Stochastic Gradient Langevin Dynamics (SGLD) algorithm and propose a novel SG-MCMC algorithm referred to as Stochastic Gradient Richardson-Romberg Langevin Dynamics (SGRRLD).
no code implementations • 10 Feb 2016 • Umut Şimşekli, Roland Badeau, A. Taylan Cemgil, Gaël Richard
These second order methods directly approximate the inverse Hessian by using a limited history of samples and their gradients.