3 papers
cs.SD2025
Multi-Class-Token Transformer for Multitask Self-supervised Music Information Retrieval
Yuexuan Kong, Vincent Lostanlen, Romain Hennequin +2
Contrastive learning and equivariant learning are effective methods for self-supervised learning (SSL) for audio content analysis. Yet, their application to music information retri…
cs.LG2025
Aliasing in Convnets: A Frame-Theoretic Perspective
Daniel Haider, Vincent Lostanlen, Martin Ehler +2
Using a stride in a convolutional layer inherently introduces aliasing, which has implications for numerical stability and statistical generalization. While techniques such as the…
cs.SD2024
Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement
Daniel Haider, Felix Perfler, Vincent Lostanlen +2
Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics o…