Hybrid and Interpretable Deep neural audio machines

Project Information

HI-Audio

Grant agreement ID: 101052978

DOI

10.3030/101052978

EC signature date 20 July 2022

Start date 1 October 2022

End date 30 September 2027

Funded under

• European Research Council (ERC)

Total cost

€ 2 482 317,50

EU contribution

€ 2 482 317,50

Coordinated by

INSTITUT MINES-TELECOM
France

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (14)

Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport

Author(s): Torres, Bernardo; Peeters, Geoffroy; Richard, Gaël
Published in: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Publisher: IEEE
DOI: 10.48550/arxiv.2312.14507

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

Author(s): Haocheng Liu, Teysir Baoueb, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
Published in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Issue 33, 2024
Publisher: IEEE
DOI: 10.1109/ICASSP48485.2024.10446058

Learning Source Disentanglement in Neural Audio Codec

Author(s): Xiaoyu Bie, Xubo Liu, Gaël Richard
Published in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Publisher: IEEE

Transfer Learning and Bias Correction with Pre-trained Audio Embeddings

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

A Fully Differentiable Model for Unsupervised Singing Voice Separation

Author(s): Richard, Gael; Chouteau, Pierre; Torres, Bernardo
Published in: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Publisher: IEEE
DOI: 10.48550/arxiv.2401.16837

Using Random codebooks for random neural autoencoders

Author(s): Benoît Giniès, Xiaoyu Bie, Olivier Fercoq, Gaël Richard
Published in: European Signal Processing Conference (EUSIPCO), 2024
Publisher: EURASIP

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

Author(s): Baoueb, Teysir; Liu, Haocheng; Fontaine, Mathieu; Le Roux, Jonathan; Richard, Gael
Published in: IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2024, Seoul, South Korea, 2024
Publisher: IEEE
DOI: 10.48550/arxiv.2402.01753

Speech dereverberation constrained on room impulse response characteristics.

Author(s): Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard
Published in: INTERSPEECH, 2024
Publisher: ISCA

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

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

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

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

A Hybrid Model for Weakly-Supervised Speech Dereverberation

Author(s): Louis Bahrman, Mathieu Fontaine, Gaël Richard
Published in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
Publisher: IEEE

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

Author(s): eysir Baoueb, Xiaoyu Bie, Hicham Janati, Gael Richard
Published in: IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2024), 2024
Publisher: IEEE

Singer Identity Representation Learning Using Self-Supervised Techniques

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

Structure-Informed Positional Encoding for Music Generation

Author(s): Manvi Agarwal, Changhong Wang, Gaël Richard
Published in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Issue 2, 2024
Publisher: IEEE
DOI: 10.1109/ICASSP48485.2024.10448149

Peer reviewed articles (2)

Model-Based Deep Learning for Music Information Research

Author(s): Gaël Richard, Vincent Lostanlen, Yi-Hsuan Yang, Meinard Müller
Published in: IEEE Signal Processing Magazine, 2024, ISSN 1558-0792
Publisher: IEEE
DOI: 10.1109/MSP.2024.3415569

Unsupervised Music Source Separation Using Differentiable Parametric Source Models

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

Other (3)

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

Author(s): Jose Manuel Gil Panal, Aurélien David, Gaël Richard.
Published in: Late Breaking Demo – International Society for Music Information Retrieval Conference (ISMIR), 2023
Publisher: ISMIR

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

Author(s): Jose Manuel Gil Panal, Aurelien David, Gaël Richard
Published in: Late breaking Demos - ISMIR 2024, 2024
Publisher: ISMIR

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

Author(s): Manvi Agarwal, Changhong Wang, Gaël Richard
Published in: Zenodo, 2024
Publisher: Zenodo