Wenwu Wang

A new approach to audio captioning reduces reliance on paired data.

Exploring technology's role in enhancing fish farming efficiency and welfare.

New dataset improves audio generation from detailed text descriptions.

FlowSep introduces a fresh method for extracting sounds using language queries.

A new model improves identifying and locating sounds effectively.

Discover how machines are learning to understand and describe audio like humans.

SyncFlow merges audio and video generation for seamless content creation.