Hybrid and Interpretable Deep neural audio machines

Informazioni relative al progetto

HI-Audio

ID dell’accordo di sovvenzione: 101052978

DOI

10.3030/101052978

Data della firma CE 20 Luglio 2022

Data di avvio 1 Ottobre 2022

Data di completamento 30 Settembre 2027

Finanziato da

• European Research Council (ERC)

Costo totale

€ 2 482 317,50

Contributo UE

€ 2 482 317,50

Coordinato da

INSTITUT MINES-TELECOM
France

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Conference proceedings (14)

Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport

Autori: Torres, Bernardo; Peeters, Geoffroy; Richard, Gaël
Pubblicato in: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Editore: IEEE
DOI: 10.48550/arxiv.2312.14507

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

Autori: Haocheng Liu, Teysir Baoueb, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
Pubblicato in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Numero 33, 2024
Editore: IEEE
DOI: 10.1109/ICASSP48485.2024.10446058

Learning Source Disentanglement in Neural Audio Codec

Autori: Xiaoyu Bie, Xubo Liu, Gaël Richard
Pubblicato in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editore: IEEE

Transfer Learning and Bias Correction with Pre-trained Audio Embeddings

Autori: Wang, Changhong; Richard, Gaël; Mcfee, Brian
Pubblicato in: International Society for Music Information Retrieval Conference (ISMIR 2023), Nov. 2023, Milan, Italy, 2023
Editore: ISMIR
DOI: 10.5281/zenodo.10265222

A Fully Differentiable Model for Unsupervised Singing Voice Separation

Autori: Richard, Gael; Chouteau, Pierre; Torres, Bernardo
Pubblicato in: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Editore: IEEE
DOI: 10.48550/arxiv.2401.16837

Using Random codebooks for random neural autoencoders

Autori: Benoît Giniès, Xiaoyu Bie, Olivier Fercoq, Gaël Richard
Pubblicato in: European Signal Processing Conference (EUSIPCO), 2024
Editore: EURASIP

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

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

Speech dereverberation constrained on room impulse response characteristics.

Autori: Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
Pubblicato in: INTERSPEECH, 2024
Editore: ISCA

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

Autori: Victor Deng, Changhong Wang, Gaël Richard, Brian McFee
Pubblicato in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editore: IEEE
DOI: 10.48550/arXiv.2501.15900

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

Autori: Manvi Agarwal, Changhong Wang, Gaël Richard
Pubblicato in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editore: IEEE
DOI: 10.48550/arXiv.2502.10491

A Hybrid Model for Weakly-Supervised Speech Dereverberation

Autori: Louis Bahrman, Mathieu Fontaine, Gaël Richard
Pubblicato in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Editore: IEEE

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

Autori: eysir Baoueb, Xiaoyu Bie, Hicham Janati, Gael Richard
Pubblicato in: IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2024), 2024
Editore: IEEE

Singer Identity Representation Learning Using Self-Supervised Techniques

Autori: Torres, Bernardo; Lattner, Stefan; Richard, Gael
Pubblicato in: International Society for Music Information Retrieval Conference (ISMIR 2023), Nov 2023, Milan, Italy, 2023
Editore: IEEE
DOI: 10.48550/arxiv.2401.05064

Structure-Informed Positional Encoding for Music Generation

Autori: Manvi Agarwal, Changhong Wang, Gaël Richard
Pubblicato in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Numero 2, 2024
Editore: IEEE
DOI: 10.1109/ICASSP48485.2024.10448149

Peer reviewed articles (2)

Model-Based Deep Learning for Music Information Research

Autori: Gaël Richard, Vincent Lostanlen, Yi-Hsuan Yang, Meinard Müller
Pubblicato in: IEEE Signal Processing Magazine, 2024, ISSN 1558-0792
Editore: IEEE
DOI: 10.1109/MSP.2024.3415569

Unsupervised Music Source Separation Using Differentiable Parametric Source Models

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

Other (3)

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

Autori: Jose Manuel Gil Panal, Aurélien David, Gaël Richard.
Pubblicato in: Late Breaking Demo – International Society for Music Information Retrieval Conference (ISMIR), 2023
Editore: ISMIR

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

Autori: Jose Manuel Gil Panal, Aurelien David, Gaël Richard
Pubblicato in: Late breaking Demos - ISMIR 2024, 2024
Editore: ISMIR

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

Autori: Manvi Agarwal, Changhong Wang, Gaël Richard
Pubblicato in: Zenodo, 2024
Editore: Zenodo