3 papers
cs.LG2025
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…
cs.SD2025
Hybrid Losses for Hierarchical Embedding Learning
Haokun Tian, Stefan Lattner, Brian McFee +1
In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By l…
cs.AI2025
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…