The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

Imagine standing on a street corner in the city. With your eyes closed you can hear and
recognize a succession of sounds: cars passing by, people speaking, their footsteps when …

We propose Wav2CLIP, a robust audio representation learning method by distilling from
Contrastive Language-Image Pre-training (CLIP). We systematically evaluate Wav2CLIP on …

The ability of artificial intelligence (AI) systems to perceive and comprehend audio signals is
crucial for many applications. Although significant progress has been made in this area …

Inspired by the recent progress in self-supervised learning for computer vision that
generates supervision using data augmentations, we explore a new general-purpose audio …

Learning to classify time series with limited data is a practical yet challenging problem.
Current methods are primarily based on hand-designed feature extraction rules or domain …

Recent general-purpose audio representations show state-of-the-art performance on
various audio tasks. These representations are pre-trained by self-supervised learning …

While deep learning has enabled great advances in many areas of music, labeled music
datasets remain especially hard, expensive, and time-consuming to create. In this work, we …

COVID-19 heavily affects breathing and voice and causes symptoms that make patients'
voices distinctive, creating recognizable audio signatures. Initial studies have already …

Open generative models are vitally important for the community, allowing for fine-tunes and
serving as baselines when presenting new models. However, most current text-to-audio …