Hybrid and Interpretable Deep neural audio machines

Información del proyecto

HI-Audio

Identificador del acuerdo de subvención: 101052978

DOI

10.3030/101052978

Fecha de la firma de la CE 20 Julio 2022

Fecha de inicio 1 Octubre 2022

Fecha de finalización 30 Septiembre 2027

Financiado con arreglo a

• European Research Council (ERC)

Coste total

€ 2 482 317,50

Aportación de la UE

€ 2 482 317,50

Coordinado por

INSTITUT MINES-TELECOM
France

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (14)

Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport

Autores: Torres, Bernardo; Peeters, Geoffroy; Richard, Gaël
Publicado en: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Editor: IEEE
DOI: 10.48550/arxiv.2312.14507

GLA-GRAD: A Griffin-Lim Extended Waveform Generation Diffusion Model

Autores: Haocheng Liu, Teysir Baoueb, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
Publicado en: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Edición 33, 2024
Editor: IEEE
DOI: 10.1109/ICASSP48485.2024.10446058

Learning Source Disentanglement in Neural Audio Codec

Autores: Xiaoyu Bie, Xubo Liu, Gaël Richard
Publicado en: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editor: IEEE

Transfer Learning and Bias Correction with Pre-trained Audio Embeddings

Autores: Wang, Changhong; Richard, Gaël; Mcfee, Brian
Publicado en: International Society for Music Information Retrieval Conference (ISMIR 2023), Nov. 2023, Milan, Italy, 2023
Editor: ISMIR
DOI: 10.5281/zenodo.10265222

A Fully Differentiable Model for Unsupervised Singing Voice Separation

Autores: Richard, Gael; Chouteau, Pierre; Torres, Bernardo
Publicado en: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Editor: IEEE
DOI: 10.48550/arxiv.2401.16837

Using Random codebooks for random neural autoencoders

Autores: Benoît Giniès, Xiaoyu Bie, Olivier Fercoq, Gaël Richard
Publicado en: European Signal Processing Conference (EUSIPCO), 2024
Editor: EURASIP

SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis

Autores: Baoueb, Teysir; Liu, Haocheng; Fontaine, Mathieu; Le Roux, Jonathan; Richard, Gael
Publicado en: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Editor: IEEE
DOI: 10.48550/arxiv.2402.01753

Speech dereverberation constrained on room impulse response characteristics.

Autores: Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
Publicado en: INTERSPEECH, 2024
Editor: ISCA

Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects

Autores: Victor Deng, Changhong Wang, Gaël Richard, Brian McFee
Publicado en: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editor: IEEE
DOI: 10.48550/arXiv.2501.15900

F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation

Autores: Manvi Agarwal, Changhong Wang, Gaël Richard
Publicado en: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editor: IEEE
DOI: 10.48550/arXiv.2502.10491

A Hybrid Model for Weakly-Supervised Speech Dereverberation

Autores: Louis Bahrman, Mathieu Fontaine, Gaël Richard
Publicado en: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editor: IEEE

WaveTransfer: A Flexible End-to-end Multi-instrument Timbre Transfer with Diffusion

Autores: eysir Baoueb, Xiaoyu Bie, Hicham Janati, Gael Richard
Publicado en: IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2024), 2024
Editor: IEEE

Singer Identity Representation Learning Using Self-Supervised Techniques

Autores: Torres, Bernardo; Lattner, Stefan; Richard, Gael
Publicado en: International Society for Music Information Retrieval Conference (ISMIR 2023), Nov 2023, Milan, Italy, 2023
Editor: IEEE
DOI: 10.48550/arxiv.2401.05064

Structure-Informed Positional Encoding for Music Generation

Autores: Manvi Agarwal, Changhong Wang, Gaël Richard
Publicado en: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Edición 2, 2024
Editor: IEEE
DOI: 10.1109/ICASSP48485.2024.10448149

Peer reviewed articles (2)

Model-Based Deep Learning for Music Information Research

Autores: Gaël Richard, Vincent Lostanlen, Yi-Hsuan Yang, Meinard Müller
Publicado en: IEEE Signal Processing Magazine, 2024, ISSN 1558-0792
Editor: IEEE
DOI: 10.1109/MSP.2024.3415569

Unsupervised Music Source Separation Using Differentiable Parametric Source Models

Autores: Kilian Schulze-Forster; Gaël Richard; Liam Kelley; Clement S. J. Doire; Roland Badeau
Publicado en: IEEE/ACM Transactions on Audio, Speech and Language Processing, 2023, ISSN 2329-9290
Editor: IEEE
DOI: 10.1109/TASLP.2023.3252272

Other (3)

The HI-Audio Online platform for distributed music crowdsourcing database collection.

Autores: Jose Manuel Gil Panal, Aurélien David, Gaël Richard.
Publicado en: Late Breaking Demo – International Society for Music Information Retrieval Conference (ISMIR), 2023
Editor: ISMIR

Hi-Audio online platform: opportunities and challenges of collecting varied music data on the web

Autores: Jose Manuel Gil Panal, Aurelien David, Gaël Richard
Publicado en: Late breaking Demos - ISMIR 2024, 2024
Editor: ISMIR

"Dataset and Checkpoints for ""Structure-Informed Positional Encoding for Music Generation"""

Autores: Manvi Agarwal, Changhong Wang, Gaël Richard
Publicado en: Zenodo, 2024
Editor: Zenodo