Accurate tempo estimation based on harmonic + noise decomposition

Autor: Bertrand David, Gael Richard, Miguel Alonso

Publikováno v: EURASIP Journal on Advances in Signal Processing, Vol 2007 (2007)

We present an innovative tempo estimation system that processes acoustic audio signals and does not use any high-level musical knowledge. Our proposal relies on a harmonic + noise decomposition of the audio signal by means of a subspace analysis meth

Externí odkaz: https://doaj.org/article/a731062a90a746399408b94459905c1f

Phase Shifted Bedrosian Filterbank: An Interpretable Audio Front-End for Time-Domain Audio Source Separation

Autor: Felix Mathieu, Thomas Courtat, Gael Richard, Geoffroy Peeters

Publikováno v: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5140065207e907d4a9c71f32f99d22c6
https://doi.org/10.1109/icassp43922.2022.9746122

Self-Supervised VQ-VAE for One-Shot Music Style Transfer

Autor: Gael Richard, Ondrej Cifka, Umut Simsekli, Alexey Ozerov

Publikováno v: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP
ICASSP 2021-IEEE International Conference on Acoustics, Speech and Signal Processing
ICASSP 2021-IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2021, Toronto / Virtual, Canada. ⟨10.1109/ICASSP39728.2021.9414235⟩

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 introduction. In contrast, related tasks in the music audio domain remaine

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ecde29af283777dd42e6ae6d06a40c09
http://arxiv.org/abs/2102.05749

VQCPC-GAN: Variable-Length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding

Autor: Javier Nistal, Cyran Aouameur, Stefan Lattner, Gael Richard

Publikováno v: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct 2021, New Paltz, United States
2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)

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". However, in the (musical) audio domain, it is

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d9a009935e5c6c5997c3b37ec9237d2

Confidence-based Weighted Loss for Multi-label Classification with Missing Labels

Autor: Gael Richard, Elena V. Epure, Karim M. Ibrahim, Geoffroy Peeters

Publikováno v: The 2020 International Conference on Multimedia Retrieval (ICMR '20)
The 2020 International Conference on Multimedia Retrieval (ICMR '20), Jun 2020, Dublin, Ireland. ⟨10.1145/3372278.3390728⟩
Proceedings of the 2020 International Conference on Multimedia Retrieval
ICMR

International audience; The problem of multi-label classification with missing labels (MLML) is a common challenge that is prevalent in several domains, e.g. image annotation and auto-tagging. In multi-label classification, each instance may belong t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd82fa724e5a911d24d9773b0306c8ef
https://hal.archives-ouvertes.fr/hal-02547012/file/ICMR_paper_v5.3.pdf