Music tagging and content-based retrieval systems have traditionally been constructed
using pre-defined ontologies covering a rigid set of music attributes or text queries. This …

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

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 …

Self-supervised learning (SSL) has recently emerged as a promising paradigm for training
generalisable models on large-scale data in the fields of vision, text, and speech. Although …

Personalized recommendation serves as a ubiquitous channel for users to discover
information tailored to their interests. However, traditional recommendation models primarily …

We demonstrate that language models pre-trained on codified (discretely-encoded) music
audio learn representations that are useful for downstream MIR tasks. Specifically, we …

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

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 …

The ability to learn universal audio representations that can solve diverse speech, music,
and environment tasks can spur many applications that require general sound content …

In the era of extensive intersection between art and Artificial Intelligence (AI), such as image
generation and fiction co-creation, AI for music remains relatively nascent, particularly in …