10 papers
Sobolev Norms in Neural Embeddings Measure Audio Morphing Regularity
Théo Chasle Cauchy, Modan Tailleur, Barbara Pascal +2
Morphing has recently gained renewed interest with the emergence of generative models, particularly in audio and image generation. In musical sound synthesis, morphing can generate…
COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation
Ruike Cao, Fugen Yao, Liang Dong +3
While Large Language Models (LLMs) have achieved remarkable results across various benchmarks, their alignment with normative values often results in homogenized responses that fai…
Predicting Timbre Traits for Interpretable Assessment of Musical Sound Synthesizers
Théo Chasle Cauchy, Modan Tailleur, Lindsey Reymore +2
Measuring neural audio synthesizers' performance is now routinely conducted using distribution based metrics such as the Fréchet Audio Distance (FAD). Although this metric can be c…
Enforcing Speech Content Privacy in Environmental Sound Recordings using Segment-wise Waveform Reversal
Modan Tailleur, Mathieu Lagrange, Pierre Aumond +1
Environmental sound recordings often contain intelligible speech, raising privacy concerns that limit analysis, sharing and reuse of data. In this paper, we introduce a method that…
Sound Scene Synthesis at the DCASE 2024 Challenge
Mathieu Lagrange, Junwon Lee, Modan Tailleur +5
This paper presents Task 7 at the DCASE 2024 Challenge: sound scene synthesis. Recent advances in sound synthesis and generative models have enabled the creation of realistic and d…
Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation
Junwon Lee, Modan Tailleur, Laurie M. Heller +5
Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene…
EMVD dataset: a dataset of extreme vocal distortion techniques used in heavy metal
Modan Tailleur, Julien Pinquier, Laurent Millot +2
In this paper, we introduce the Extreme Metal Vocals Dataset, which comprises a collection of recordings of extreme vocal techniques performed within the realm of heavy metal music…
Towards better visualizations of urban sound environments: insights from interviews
Modan Tailleur, Pierre Aumond, Vincent Tourre +1
Urban noise maps and noise visualizations traditionally provide macroscopic representations of noise levels across cities. However, those representations fail at accurately gauging…
Correlation of Fréchet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant
Modan Tailleur, Junwon Lee, Mathieu Lagrange +4
This paper explores whether considering alternative domain-specific embeddings to calculate the Fréchet Audio Distance (FAD) metric can help the FAD to correlate better with percep…
Detection of Deepfake Environmental Audio
Hafsa Ouajdi, Oussama Hadder, Modan Tailleur +2
With the ever-rising quality of deep generative models, it is increasingly important to be able to discern whether the audio data at hand have been recorded or synthesized. Althoug…