| Title: |
Mind the Prompt: Prompting Strategies in Audio Generations for Improving Sound Classification |
| Authors: |
F. Ronchini; HH. Wu; WC. Lin; F. Antonacci |
| Contributors: |
Ronchini, F.; Wu, Hh.; Lin, Wc.; Antonacci, F. |
| Publication Year: |
2025 |
| Collection: |
RE.PUBLIC@POLIMI - Research Publications at Politecnico di Milano |
| Description: |
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. |
| Document Type: |
conference object |
| Language: |
English |
| Relation: |
info:eu-repo/semantics/altIdentifier/isbn/9798331519315; info:eu-repo/semantics/altIdentifier/wos/WOS:001547041200026; ispartofbook:2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW); 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW); firstpage:1; lastpage:5; numberofpages:5; https://hdl.handle.net/11311/1295746 |
| DOI: |
10.1109/ICASSPW65056.2025.11011113 |
| Availability: |
https://hdl.handle.net/11311/1295746; https://doi.org/10.1109/ICASSPW65056.2025.11011113 |
| Accession Number: |
edsbas.628C0BED |
| Database: |
BASE |