Meet LP-MusicCaps: A Tag-to-Pseudo Caption Generation Approach with Large Language Models to Address the Data Scarcity Issue in Automatic Music Captioning
Marktechpost
AUGUST 3, 2023
Subsequently, a team of researchers from South Korea has developed a method called LP-MusicCaps (Large language-based Pseudo music caption dataset), creating a music captioning dataset by applying LLMs carefully to tagging datasets. This resulted in the generation of approximately 2.2M captions paired with 0.5M audio clips.
Let's personalize your content