| Neural vocoding for singing and speaking voices with the multi-band excited wavenet A Roebel, F Bous Information 13 (3), 103, 2022 | 10 | 2022 |
| Analysing deep learning-spectral envelope prediction methods for singing synthesis F Bous, A Roebel 2019 27th European Signal Processing Conference (EUSIPCO), 1-5, 2019 | 7 | 2019 |
| A bottleneck auto-encoder for f0 transformations on speech and singing voice F Bous, A Roebel Information 13 (3), 102, 2022 | 6 | 2022 |
| Voice Reenactment with F0 and timing constraints and adversarial learning of conversions F Bous, L Benaroya, N Obin, A Roebel 2022 30th European Signal Processing Conference (EUSIPCO), 389-393, 2022 | 4 | 2022 |
| Towards universal neural vocoding with a multi-band excited wavenet A Roebel, F Bous arXiv preprint arXiv:2110.03329, 2021 | 4 | 2021 |
| Analysis and Transformation of Voice Level in Singing Voice F Bous, A Roebel ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 3 | 2023 |
| Semi-supervised learning of glottal pulse positions in a neural analysis-synthesis framework F Bous, L Ardaillon, A Roebel 2020 28th European Signal Processing Conference (EUSIPCO), 401-405, 2021 | 2 | 2021 |
| A neural voice transformation framework for modification of pitch and intensity F Bous Sorbonne université, 2023 | 1 | 2023 |
| Sequence-to-sequence voice conversion using F0 and time conditioning and adversarial learning F Bous, L Benaroya, N Obin, A Roebel CoRR, 2021 | 1 | 2021 |
| VaSAB: The variable size adaptive information bottleneck for disentanglement on speech and singing voice F Bous, A Roebel arXiv preprint arXiv:2310.03444, 2023 | | 2023 |
Axel RoebelIRCAM (STMS Laboratory)Adresse e-mail validée de ircam.fr
