3 citations · 9 across the 15 of their papers we have counts for
16 papers
A Self-Supervised Approach for Minimal-Annotation Hydroacoustic Data Exploration
Pierre-Yves Raumer, Axel Marmoret, Dorian Cazau +6
Passive hydroacoustic monitoring often generates large volumes of continuous recordings that are only partially exploited due to the cost of manual annotation. Supervised detection…
Can pre-trained Deep Learning models predict groove ratings?
Axel Marmoret, Nicolas Farrugia, Jan Alexander Stupacher
This study explores the extent to which deep learning models can predict groove and its related perceptual dimensions directly from audio signals. We critically examine the effecti…
Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers
Jonathan Lys, Vincent Gripon, Bastien Pasdeloup +4
Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignme…
Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training
Jonathan Lys, Vincent Gripon, Bastien Pasdeloup +4
Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often obtained as the sum of two contri…
Unsupervised Evaluation of Deep Audio Embeddings for Music Structure Analysis
Axel Marmoret
Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces. State-of-the-art methods are often based on supervised deep learning, but these method…
D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding
Jonathan Lys, Vincent Gripon, Axel Marmoret +4
Discrete diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied. Standard autoregressive sear…
TensLoRA: Tensor Alternatives for Low-Rank Adaptation
Axel Marmoret, Reda Bensaid, Jonathan Lys +2
Low-Rank Adaptation (LoRA) is widely used to efficiently adapt Transformers by adding trainable low-rank matrices to attention projections. While effective, these matrices are cons…
AutoMashup: Automatic Music Mashups Creation
Marine Delabaere, Léa Miqueu, Michael Moreno +8
We introduce AutoMashup, a system for automatic mashup creation based on source separation, music analysis, and compatibility estimation. We propose using COCOLA to assess compatib…
Barwise Music Structure Analysis with the Correlation Block-Matching Segmentation Algorithm
Axel Marmoret, Jérémy E. Cohen, Frédéric Bimbot
Music Structure Analysis (MSA) is a Music Information Retrieval task consisting of representing a song in a simplified, organized manner by breaking it down into sections typically…
Polytopic Analysis of Music
Axel Marmoret, Jérémy E. Cohen, Frédéric Bimbot
Structural segmentation of music refers to the task of finding a symbolic representation of the organisation of a song, reducing the musical flow to a partition of non-overlapping…
Convolutive Block-Matching Segmentation Algorithm with Application to Music Structure Analysis
Axel Marmoret, Jérémy E. Cohen, Frédéric Bimbot
Music Structure Analysis (MSA) consists of representing a song in sections (such as ``chorus'', ``verse'', ``solo'' etc), and can be seen as the retrieval of a simplified organizat…
Semi-Supervised Convolutive NMF for Automatic Piano Transcription
Haoran Wu, Axel Marmoret, Jérémy E. Cohen
Automatic Music Transcription, which consists in transforming an audio recording of a musical performance into symbolic format, remains a difficult Music Information Retrieval task…
Barwise Compression Schemes for Audio-Based Music Structure Analysis
Axel Marmoret, Jérémy E. Cohen, Frédéric Bimbot
Music Structure Analysis (MSA) consists in segmenting a music piece in several distinct sections. We approach MSA within a compression framework, under the hypothesis that the stru…
Exploring single-song autoencoding schemes for audio-based music structure analysis
Axel Marmoret, Jérémy E. Cohen, Frédéric Bimbot
The ability of deep neural networks to learn complex data relations and representations is established nowadays, but it generally relies on large sets of training data. This work e…
Nonnegative Tucker Decomposition with Beta-divergence for Music Structure Analysis of Audio Signals
Axel Marmoret, Florian Voorwinden, Valentin Leplat +2
Nonnegative Tucker decomposition (NTD), a tensor decomposition model, has received increased interest in the recent years because of its ability to blindly extract meaningful patte…
Uncovering audio patterns in music with Nonnegative Tucker Decomposition for structural segmentation
Axel Marmoret, Jérémy E. Cohen, Nancy Bertin +1
Recent work has proposed the use of tensor decomposition to model repetitions and to separate tracks in loop-based electronic music. The present work investigates further on the ab…