Axel Roebel - RankMe

73 papers A 11Misc 13Journal 35Unranked 13

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Continuous Audio Language Models. CoRR Simon Rouard, Manu Orsini, Axel Roebel, Neil Zeghidour, Alexandre Défossez
2025	J	`jnl`	Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters. CoRR Mathilde Abrassart, Nicolas Obin, Axel Roebel
2025	Misc	`conf`	MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling. ICASSP Simon Rouard, Robin San Roman, Yossi Adi, Axel Roebel
2025	J	`jnl`	MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling. CoRR Simon Rouard, Robin San Roman, Yossi Adi, Axel Roebel
2025	J	`jnl`	PitchFlower: A flow-based neural audio codec with pitch controllability. CoRR Diego Torres, Axel Roebel, Nicolas Obin
2024	—	`conf`	Audio Conditioning for Music Generation via Discrete Bottleneck Features. ISMIR Simon Rouard, Yossi Adi, Jade Copet, Axel Roebel, Alexandre Défossez
2024	J	`jnl`	Audio Conditioning for Music Generation via Discrete Bottleneck Features. CoRR Simon Rouard, Yossi Adi, Jade Copet, Axel Roebel, Alexandre Défossez
2024	J	`jnl`	Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis. CoRR Théodor Lemerle, Harrison Vanderbyl, Vaibhav Srivastav, Nicolas Obin, Axel Roebel
2024	—	`conf`	On Strategies to Exploit Dependencies Between Singing Voice Alignment and Separation. EUSIPCO Théo Nguyen, Yann Teytaut, Axel Roebel
2024	A	`conf`	Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis. INTERSPEECH Théodor Lemerle, Nicolas Obin, Axel Roebel
2024	J	`jnl`	Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis. CoRR Théodor Lemerle, Nicolas Obin, Axel Roebel
2023	J	`jnl`	AI (r)evolution - where are we heading? Thoughts about the future of music and sound technologies in the era of deep learning. CoRR Giovanni Bindi, Nils Demerlé, Rodrigo Diaz, David Genova, Aliénor Golvet, Ben Hayes, Jiawen Huang, Lele Liu, Vincent Martos, Sarah Nabi, Teresa Pelinski, Lenny Renault, Saurjya Sarkar, Pedro Sarmento, Cyrus Vahidi, Lewis Wolstanholme, Yixiao Zhang, Axel Roebel, Nick Bryan-Kinns, Jean-Louis Giavitto, Mathieu Barthet
2023	Misc	`conf`	Analysis and Transformation of Voice Level in Singing Voice. ICASSP Frederik Bous, Axel Roebel
2023	J	`jnl`	Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations. Entropy Laurent Benaroya, Nicolas Obin, Axel Roebel
2023	J	`jnl`	VaSAB: The variable size adaptive information bottleneck for disentanglement on speech and singing voice. CoRR Frederik Bous, Axel Roebel
2022	J	`jnl`	A Bottleneck Auto-Encoder for F0 Transformations on Speech and Singing Voice. Inf. Frederik Bous, Axel Roebel
2022	A	`conf`	A study on constraining Connectionist Temporal Classification for temporal audio alignment. INTERSPEECH Yann Teytaut, Baptiste Bouvier, Axel Roebel
2022	J	`jnl`	Analysis and transformations of intensity in singing voice. CoRR Frederik Bous, Axel Roebel
2022	J	`jnl`	Audio Defect Detection in Music with Deep Networks. CoRR Daniel Wolff, Rémi Mignot, Axel Roebel
2022	J	`jnl`	Neural Vocoding for Singing and Speaking Voices with the Multi-Band Excited WaveNet. Inf. Axel Roebel, Frederik Bous
2022	A	`conf`	Production Strategies of Vocal Attitudes. INTERSPEECH Léane Salais, Pablo Arias, Clément Le Moine, Victor Rosi, Yann Teytaut, Nicolas Obin, Axel Roebel
2022	—	`conf`	StyleWaveGAN: Style-based synthesis of drum sounds using generative adversarial networks for higher audio quality. EUSIPCO Antoine Lavault, Axel Roebel, Matthieu Voiry
2022	J	`jnl`	StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks. CoRR Antoine Lavault, Axel Roebel, Matthieu Voiry
2022	—	`conf`	Voice Reenactment with F0 and timing constraints and adversarial learning of conversions. EUSIPCO Frederik Bous, Laurent Benaroya, Nicolas Obin, Axel Roebel
2021	—	`conf`	Audio Defect Detection in Music with Deep Networks. ISMIR Daniel Wolff, Rémi Mignot, Axel Roebel
2021	J	`jnl`	Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations. CoRR Laurent Benaroya, Nicolas Obin, Axel Roebel
2021	A	`conf`	Phoneme-to-Audio Alignment with Recurrent Neural Networks for Speaking and Singing Voice. Interspeech Yann Teytaut, Axel Roebel
2021	J	`jnl`	Sequence-To-Sequence Voice Conversion using F0 and Time Conditioning and Adversarial Learning. CoRR Frederik Bous, Laurent Benaroya, Nicolas Obin, Axel Roebel
2021	A	`conf`	Speaker Attentive Speech Emotion Recognition. Interspeech Clément Le Moine, Nicolas Obin, Axel Roebel
2021	J	`jnl`	Speaker Attentive Speech Emotion Recognition. CoRR Clément Le Moine, Nicolas Obin, Axel Roebel
2021	J	`jnl`	Towards Universal Neural Vocoding with a Multi-band Excited WaveNet. CoRR Axel Roebel, Frederik Bous
2021	—	`conf`	Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels. EUSIPCO Clément Le Moine, Nicolas Obin, Axel Roebel
2021	J	`jnl`	Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels. CoRR Clément Le Moine Veillon, Nicolas Obin, Axel Roebel
2020	—	`conf`	CycleGAN Voice Conversion of Spectral Envelopes using Adversarial Weights. EUSIPCO Rafael Ferro, Nicolas Obin, Axel Roebel
2020	Misc	`conf`	GCI Detection from Raw Speech Using a Fully-Convolutional Network. ICASSP Luc Ardaillon, Axel Roebel
2020	—	`conf`	La voix actée : pratiques, enjeux, applications (Acted voice : practices, challenges, applications). JEP-TALN-RECITAL (1) Mathias Quillot, Lauriane Guillou, Adrien Gresse, Rafaël Ferro, Raphaël Roth, Damien Malinas, Richard Dufour, Axel Roebel, Nicolas Obin, Jean-François Bonastre, Emmanuel Ethis
2020	J	`jnl`	Realistic Transformation of Facial and Vocal Smiles in Real-Time Audiovisual Streams. IEEE Trans. Affect. Comput. Pablo Arias, Catherine Soladié, Oussema Bouafif, Axel Roebel, Renaud Séguier, Jean-Julien Aucouturier
2020	—	`conf`	Semi-supervised learning of glottal pulse positions in a neural analysis-synthesis framework. EUSIPCO Frederik Bous, Luc Ardaillon, Axel Roebel
2020	J	`jnl`	Semi-supervised learning of glottal pulse positions in a neural analysis-synthesis framework. CoRR Frederik Bous, Luc Ardaillon, Axel Roebel
2020	Misc	`conf`	Sound Texture Synthesis Using RI Spectrograms. ICASSP Hugo Caracalla, Axel Roebel
2019	—	`conf`	Analysing Deep Learning-Spectral Envelope Prediction Methods for Singing Synthesis. EUSIPCO Frederik Bous, Axel Roebel
2019	J	`jnl`	Analysing Deep Learning-Spectral Envelope Prediction Methods for Singing Synthesis. CoRR Frederik Bous, Axel Roebel
2019	J	`jnl`	Data Augmentation for Drum Transcription with Convolutional Neural Networks. CoRR Céline Jacques, Axel Roebel
2019	A	`conf`	Fully-Convolutional Network for Pitch Estimation of Speech Signals. INTERSPEECH Luc Ardaillon, Axel Roebel
2019	—	`conf`	Improving singing voice separation using Deep U-Net and Wave-U-Net with data augmentation. EUSIPCO Alice Cohen-Hadria, Axel Roebel, Geoffroy Peeters
2019	J	`jnl`	Improving singing voice separation using Deep U-Net and Wave-U-Net with data augmentation. CoRR Alice Cohen-Hadria, Axel Roebel, Geoffroy Peeters
2019	Misc	`conf`	Sequence-to-sequence Modelling of F0 for Speech Emotion Conversion. ICASSP Carl Robinson, Nicolas Obin, Axel Roebel
2019	J	`jnl`	SoftGAN: Learning generative models efficiently with application to CycleGAN Voice Conversion. CoRR Rafael Ferro, Nicolas Obin, Axel Roebel
2019	J	`jnl`	Sound texture synthesis using RI spectrograms. CoRR Hugo Caracalla, Axel Roebel
2019	J	`jnl`	Sound texture synthesis using convolutional neural networks. CoRR Hugo Caracalla, Axel Roebel
2018	J	`jnl`	Binaural Localization of Multiple Sound Sources by Non-Negative Tensor Factorization. IEEE ACM Trans. Audio Speech Lang. Process. Elie-Laurent Benaroya, Nicolas Obin, Marco Liuni, Axel Roebel, Wilson Raumel, Sylvain Argentieri
2017	A	`conf`	A Mouth Opening Effect Based on Pole Modification for Expressive Singing Voice Transformation. INTERSPEECH Luc Ardaillon, Axel Roebel
2016	J	`jnl`	A Morphological Model for Simulating Acoustic Scenes and Its Application to Sound Event Detection. IEEE ACM Trans. Audio Speech Lang. Process. Grégoire Lafay, Mathieu Lagrange, Mathias Rossignol, Emmanouil Benetos, Axel Roebel
2016	Misc	`conf`	A source/filter model with adaptive constraints for NMF-based speech separation. ICASSP Damien Bouvier, Nicolas Obin, Marco Liuni, Axel Roebel
2016	A	`conf`	Evaluation of Singing Synthesis: Methodology and Case Study with Concatenative and Performative Systems. INTERSPEECH Lionel Feugère, Christophe d'Alessandro, Samuel Delalez, Luc Ardaillon, Axel Roebel
2016	A	`conf`	Expressive Control of Singing Voice Synthesis Using Musical Contexts and a Parametric F0 Model. INTERSPEECH Luc Ardaillon, Celine Chabot-Canet, Axel Roebel
2016	J	`jnl`	Multi-Frame Amplitude Envelope Estimation for Modification of Singing Voice. IEEE ACM Trans. Audio Speech Lang. Process. Gilles Degottex, Luc Ardaillon, Axel Roebel
2016	J	`jnl`	Similarity Search of Acted Voices for Automatic Voice Casting. IEEE ACM Trans. Audio Speech Lang. Process. Nicolas Obin, Axel Roebel
2016	Misc	`conf`	Simple multi frame analysis methods for estimation of amplitude spectral envelope estimation in singing voice. ICASSP Gilles Degottex, Luc Ardaillon, Axel Roebel
2015	A	`conf`	A multi-layer F0 model for singing voice synthesis using a b-spline representation with intuitive controls. INTERSPEECH Luc Ardaillon, Gilles Degottex, Axel Roebel
2015	J	`jnl`	An evaluation framework for event detection using a morphological model of acoustic scenes. CoRR Mathieu Lagrange, Grégoire Lafay, Mathias Rossignol, Emmanouil Benetos, Axel Roebel
2015	Misc	`conf`	On automatic drum transcription using non-negative matrix deconvolution and itakura saito divergence. ICASSP Axel Roebel, Jordi Pons, Marco Liuni, Mathieu Lagrange
2015	A	`conf`	On glottal source shape parameter transformation using a novel deterministic and stochastic speech analysis and synthesis system. INTERSPEECH Stefan Huber, Axel Roebel
2015	Misc	`conf`	The role of glottal source parameters for high-quality transformation of perceptual age. ICASSP Xavier Favory, Nicolas Obin, Gilles Degottex, Axel Roebel
2014	Misc	`conf`	On automatic voice casting for expressive speech: Speaker recognition vs. speech classification. ICASSP Nicolas Obin, Axel Roebel, Grégoire Bachman
2014	J	`jnl`	On the use of a spatial cue as prior information for stereo sound source separation based on spatially weighted non-negative tensor factorization. EURASIP J. Adv. Signal Process. Yuki Mitsufuji, Axel Roebel
2014	Misc	`conf`	Online NON-negative Tensor Deconvolution for source detection in 3DTV audio. ICASSP Yuki Mitsufuji, Marco Liuni, Alex Baker, Axel Roebel
2013	Misc	`conf`	Sound source separation based on non-negative tensor factorization incorporating spatial cue as prior knowledge. ICASSP Yuki Mitsufuji, Axel Roebel
2013	—	`book`	Spectral domain analysis, modelling and transformation of sound. (Analyse, modelisation et transformation des sons). Axel Roebel
2013	Misc	`conf`	Syll-O-Matic: An adaptive time-frequency representation for the automatic segmentation of speech into syllables. ICASSP Nicolas Obin, Francois Lamare, Axel Roebel
2011	J	`jnl`	Sample Orchestrator : gestion par le contenu d'échantillons sonores. Traitement du Signal Hugues Vinet, Gérard Assayag, Juan José Burred, Grégoire Carpentier, Nicolas Misdariis, Geoffroy Peeters, Axel Roebel, Norbert Schnell, Diemo Schwarz, Damien Tardieu
2006	—	`conf`	Estimation of partial parameters for non stationary sinusoids. ICMC Axel Roebel
2004	—	`conf`	Signal decomposition by means of classification of spectral peaks. ICMC Axel Roebel, Miroslav Zivanovic, Xavier Rodet