3 papers
cs.SD2024
Enhancing Zero-shot Audio Classification using Sound Attribute Knowledge from Large Language Models
Xuenan Xu, Pingyue Zhang, Ming Yan +2
Zero-shot audio classification aims to recognize and classify a sound class that the model has never seen during training. This paper presents a novel approach for zero-shot audio…
cs.SD2024
A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds
Xuenan Xu, Xiaohang Xu, Zeyu Xie +3
Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events.…
cs.SD2024
BLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data
Xuenan Xu, Zhiling Zhang, Zelin Zhou +4
Compared with ample visual-text pre-training research, few works explore audio-text pre-training, mostly due to the lack of sufficient parallel audio-text data. Most existing metho…