8 citations · 19 across the 15 of their papers we have counts for
15 papers
Steering dense music retrieval with open-vocabulary concept discovery
Julien Guinot, Alain Riou, Elio Quinton +1
Controllable music retrieval lets users find music that is, for example, more ambient, less distorted, or without guitar while preserving the other semantic content of an original…
On the Geometry of Music Bandwidth Extension in Latent Spaces of Audio Codecs
Hendrik Vincent Koops, Hao Hao Tan, Elio Quinton
Recent audio restoration increasingly relies on large-scale conditional latent generative modeling, including diffusion, Schrodinger Bridges, and Flow Matching variants, to invert…
Single-step Controllable Music Bandwidth Extension With Flow Matching
Carlos Hernandez-Olivan, Hendrik Vincent Koops, Hao Hao Tan +1
Audio restoration consists in inverting degradations of a digital audio signal to recover what would have been the pristine quality signal before the degradation occurred. This is…
Not All Deepfakes Are Created Equal: Triaging Audio Forgeries for Robust Deepfake Singer Identification
Davide Salvi, Hendrik Vincent Koops, Elio Quinton
The proliferation of highly realistic singing voice deepfakes presents a significant challenge to protecting artist likeness and content authenticity. Automatic singer identificati…
GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models
Julien Guinot, Elio Quinton, György Fazekas
Multimodal contrastive models have achieved strong performance in text-audio retrieval and zero-shot settings, but improving joint embedding spaces remains an active research area.…
SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding
Julien Guinot, Alain Riou, Elio Quinton +1
Joint embedding spaces have significantly advanced music understanding and generation by linking text and audio through multimodal contrastive learning. However, these approaches f…
Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks
Christos Plachouras, Julien Guinot, George Fazekas +3
Downstream probing has been the dominant method for evaluating model representations, an important process given the increasing prominence of self-supervised learning and foundatio…
Leave-One-EquiVariant: Alleviating invariance-related information loss in contrastive music representations
Julien Guinot, Elio Quinton, György Fazekas
Contrastive learning has proven effective in self-supervised musical representation learning, particularly for Music Information Retrieval (MIR) tasks. However, reliance on augment…
Exploring trends in audio mixes and masters: Insights from a dataset analysis
Angeliki Mourgela, Elio Quinton, Spyridon Bissas +2
We present an analysis of a dataset of audio metrics and aesthetic considerations about mixes and masters provided by the web platform MixCheck studio. The platform is designed for…
Foundation Models for Music: A Survey
Yinghao Ma, Anders Øland, Anton Ragni +39
In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This com…
MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models
Benno Weck, Ilaria Manco, Emmanouil Benetos +3
Multimodal models that jointly process audio and language hold great promise in audio understanding and are increasingly being adopted in the music domain. By allowing users to que…
Robust Lossy Audio Compression Identification
Hendrik Vincent Koops, Gianluca Micchi, Elio Quinton
Previous research contributions on blind lossy compression identification report near perfect performance metrics on their test set, across a variety of codecs and bit rates. Howev…
Semi-Supervised Contrastive Learning of Musical Representations
Julien Guinot, Elio Quinton, György Fazekas
Despite the success of contrastive learning in Music Information Retrieval, the inherent ambiguity of contrastive self-supervision presents a challenge. Relying solely on augmentat…
The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation
Ilaria Manco, Benno Weck, SeungHeon Doh +10
We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models. The dataset…
Serenade: A Model for Human-in-the-loop Automatic Chord Estimation
Hendrik Vincent Koops, Gianluca Micchi, Ilaria Manco +1
Computational harmony analysis is important for MIR tasks such as automatic segmentation, corpus analysis and automatic chord label estimation. However, recent research into the am…