1 citations · 1 across the 16 of their papers we have counts for
21 papers
Exploring Representation Autoencoders for Text-to-Audio Generation
Bernardo V. Miranda, Hugo Malard, Gaël Richard +2
Representation autoencoders (RAE), created by pairing a frozen pretrained self-supervised learning (SSL) encoder with a trained decoder, have recently demonstrated state-of-the-art…
Probing Large Audio-Language Models for Compositional Understanding of Sounding Actions
Michel Olvera, Paraskevas Stamatiadis, Changhong Wang +1
Large audio-language models (LALMs) excel at understanding and reasoning tasks over atomic sound events, yet their ability to infer higher-level human activities from such fine-gra…
The Internet Archive Music Dataset
Paraskevas Stamatiadis, Bernardo V Miranda, Clémentine Berger +3
We introduce the Internet Archive Music Dataset (IAMD), a large-scale collection of captioned music segments derived from the Internet Archive. To the best of our knowledge, IAMD c…
Unlocking Spatial Grounding in Large Audio-Visual Retrieval models
Hugo Malard, Michel Olvera, Sanjeel Parekh +3
Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale. The task, however, remains challengi…
Taylor-SWFT: fast discrete Statistical Wave Field Theory using Taylor expansion for late reverberation Work under review
Marius Rodrigues, Louis Lalay, Roland Badeau +2
Dynamic room acoustic simulation aims to render the acoustic effects of an environment in real time while accounting for potentially moving sources and receivers. In this context,…
S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization
Zineb Lahrichi, Gaëtan Hadjeres, Gaël Richard +1
Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been appl…
GLA-Grad++: An Improved Griffin-Lim Guided Diffusion Model for Speech Synthesis
Teysir Baoueb, Xiaoyu Bie, Mathieu Fontaine +1
Recent advances in diffusion models have positioned them as powerful generative frameworks for speech synthesis, demonstrating substantial improvements in audio quality and stabili…
Melody-Lyrics Matching with Contrastive Alignment Loss
Changhong Wang, Michel Olvera, Gaël Richard
The connection between music and lyrics is far beyond semantic bonds. Conceptual pairs in the two modalities such as rhythm and rhyme, note duration and syllabic stress, and struct…
U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model
Louis Bahrman, Marius Rodrigues, Mathieu Fontaine +1
This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually unsupervised, relying sole…
Multiple Choice Learning of Low-Rank Adapters for Language Modeling
Victor Letzelter, Hugo Malard, Mathieu Fontaine +4
We propose LoRA-MCL, a training scheme that extends next-token prediction in language models with a method designed to decode diverse, plausible sentence continuations at inference…
Of All StrIPEs: Investigating Structure-informed Positional Encoding for Efficient Music Generation
Manvi Agarwal, Changhong Wang, Gael Richard
While music remains a challenging domain for generative models like Transformers, a two-pronged approach has recently proved successful: inserting musically-relevant structural inf…
F-StrIPE: Fast Structure-Informed Positional Encoding for Symbolic Music Generation
Manvi Agarwal, Changhong Wang, Gael Richard
While music remains a challenging domain for generative models like Transformers, recent progress has been made by exploiting suitable musically-informed priors. One technique to l…
A Hybrid Model for Weakly-Supervised Speech Dereverberation
Louis Bahrman, Mathieu Fontaine, Gael Richard
This paper introduces a new training strategy to improve speech dereverberation systems using minimal acoustic information and reverberant (wet) speech. Most existing algorithms re…
Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects
Victor Deng, Changhong Wang, Gael Richard +1
In recent years, foundation models have significantly advanced data-driven systems across various domains. Yet, their underlying properties, especially when functioning as feature…
Multiple Choice Learning for Efficient Speech Separation with Many Speakers
David Perera, François Derrida, Théo Mariotte +2
Training speech separation models in the supervised setting raises a permutation problem: finding the best assignation between the model predictions and the ground truth separated…
Using Random Codebooks for Audio Neural AutoEncoders
Benoît Giniès, Xiaoyu Bie, Olivier Fercoq +1
Latent representation learning has been an active field of study for decades in numerous applications. Inspired among others by the tokenization from Natural Language Processing an…
Learning Source Disentanglement in Neural Audio Codec
Xiaoyu Bie, Xubo Liu, Gaël Richard
Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound…
Speech dereverberation constrained on room impulse response characteristics
Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux +1
Single-channel speech dereverberation aims at extracting a dry speech signal from a recording affected by the acoustic reflections in a room. However, most current deep learning-ba…
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing
David Perera, Victor Letzelter, Théo Mariotte +4
We introduce Annealed Multiple Choice Learning (aMCL) which combines simulated annealing with MCL. MCL is a learning framework handling ambiguous tasks by predicting a small set of…
Winner-takes-all learners are geometry-aware conditional density estimators
Victor Letzelter, David Perera, Cédric Rommel +4
Winner-takes-all training is a simple learning paradigm, which handles ambiguous tasks by predicting a set of plausible hypotheses. Recently, a connection was established between W…
Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis
Victor Letzelter, Mathieu Fontaine, Mickaël Chen +3
We introduce Resilient Multiple Choice Learning (rMCL), an extension of the MCL approach for conditional distribution estimation in regression settings where multiple targets may b…