2025/04/04 by Francesca Ronchini, Ronchini, Francesca, Ho-Hsiang Wu +5 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning and Data Classification #Music and Audio Processing #Signal Processing (eess.SP) #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2504.03329
openalex publication_date 2025/04/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper investigates the design of effective prompt strategies for generating realistic datasets using Text-To-Audio (TTA) models. We also analyze different techniques for efficiently combining these datasets to enhance their utility in sound classification tasks. By evaluating two sound classification datasets with two TTA models, we apply a range of prompt strategies. Our findings reveal that task-specific prompt strategies significantly outperform basic prompt approaches in data generation. Furthermore, merging datasets generated using different TTA models proves to enhance classification performance more effectively than merely increasing the training dataset size. Overall, our results underscore the advantages of these methods as effective data augmentation techniques using synthetic data.