| 2025 | ICASSP | MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling. | Simon Rouard, Robin San Roman, Yossi Adi, Axel Roebel |
| 2024 | Interspeech | Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis. | Thodor Lemerle, Nicolas Obin, Axel Roebel |
| 2023 | ICASSP | Analysis and Transformation of Voice Level in Singing Voice. | Frederik Bous, Axel Roebel |
| 2022 | Interspeech | Production Strategies of Vocal Attitudes. | Lane Salais, Pablo Arias, Clment Le Moine, Victor Rosi, Yann Teytaut, Nicolas Obin, Axel Roebel |
| 2022 | Interspeech | A study on constraining Connectionist Temporal Classification for temporal audio alignment. | Yann Teytaut, Baptiste Bouvier, Axel Roebel |
| 2021 | Interspeech | Speaker Attentive Speech Emotion Recognition. | Clment Le Moine, Nicolas Obin, Axel Roebel |
| 2021 | Interspeech | Phoneme-to-Audio Alignment with Recurrent Neural Networks for Speaking and Singing Voice. | Yann Teytaut, Axel Roebel |
| 2020 | ICASSP | GCI Detection from Raw Speech Using a Fully-Convolutional Network. | Luc Ardaillon, Axel Roebel |
| 2020 | ICASSP | Sound Texture Synthesis Using RI Spectrograms. | Hugo Caracalla, Axel Roebel |
| 2019 | ICASSP | Sequence-to-sequence Modelling of F0 for Speech Emotion Conversion. | Carl Robinson, Nicolas Obin, Axel Roebel |
| 2019 | Interspeech | Fully-Convolutional Network for Pitch Estimation of Speech Signals. | Luc Ardaillon, Axel Roebel |
| 2017 | Interspeech | A Mouth Opening Effect Based on Pole Modification for Expressive Singing Voice Transformation. | Luc Ardaillon, Axel Roebel |
| 2016 | ICASSP | A source/filter model with adaptive constraints for NMF-based speech separation. | Damien Bouvier, Nicolas Obin, Marco Liuni, Axel Roebel |
| 2016 | ICASSP | Simple multi frame analysis methods for estimation of amplitude spectral envelope estimation in singing voice. | Gilles Degottex, Luc Ardaillon, Axel Roebel |
| 2016 | Interspeech | Expressive Control of Singing Voice Synthesis Using Musical Contexts and a Parametric F0 Model. | Luc Ardaillon, Celine Chabot-Canet, Axel Roebel |
| 2016 | Interspeech | Evaluation of Singing Synthesis: Methodology and Case Study with Concatenative and Performative Systems. | Lionel Feugre, Christophe d'Alessandro, Samuel Delalez, Luc Ardaillon, Axel Roebel |
| 2015 | ICASSP | The role of glottal source parameters for high-quality transformation of perceptual age. | Xavier Favory, Nicolas Obin, Gilles Degottex, Axel Roebel |
| 2015 | ICASSP | On automatic drum transcription using non-negative matrix deconvolution and itakura saito divergence. | Axel Roebel, Jordi Pons, Marco Liuni, Mathieu Lagrange |
| 2015 | Interspeech | A multi-layer F0 model for singing voice synthesis using a b-spline representation with intuitive controls. | Luc Ardaillon, Gilles Degottex, Axel Roebel |
| 2015 | Interspeech | On glottal source shape parameter transformation using a novel deterministic and stochastic speech analysis and synthesis system. | Stefan Huber, Axel Roebel |
| 2014 | ICASSP | Online NON-negative Tensor Deconvolution for source detection in 3DTV audio. | Yuki Mitsufuji, Marco Liuni, Alex Baker, Axel Roebel |
| 2014 | ICASSP | On automatic voice casting for expressive speech: Speaker recognition vs. speech classification. | Nicolas Obin, Axel Roebel, Grgoire Bachman |
| 2013 | ICASSP | Sound source separation based on non-negative tensor factorization incorporating spatial cue as prior knowledge. | Yuki Mitsufuji, Axel Roebel |
| 2013 | ICASSP | Syll-O-Matic: An adaptive time-frequency representation for the automatic segmentation of speech into syllables. | Nicolas Obin, Francois Lamare, Axel Roebel |