Similar to humans' cognitive ability to generalize knowledge and skills, self-supervised
learning (SSL) targets discovering general representations from large-scale data. This …

In the last decade, deep supervised learning has had tremendous success. However, its
flaws, such as its dependency on manual and costly annotations on large datasets and …

The massive growth of self-supervised learning (SSL) has been witnessed in language,
vision, speech, and audio domains over the past few years. While discrete label prediction is …

Deep learning architectures usually require large scale labeled datasets for achieving good
performance on general classification tasks including computer vision and natural language …

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 …

An automatic bird sound recognition system is a useful tool for collecting data of different
bird species for ecological analysis. Together with autonomous recording units (ARUs), such …

As one of the most intuitive interfaces known to humans, natural language has the potential
to mediate many tasks that involve human-computer interaction, especially in application …

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 …

Abstract visual reasoning (AVR) domain encompasses problems solving which requires the
ability to reason about relations among entities present in a given scene. While humans …

Transformers, which were originally developed for natural language processing, have
recently generated significant interest in the computer vision and audio communities due to …