2024/03/26 by Francesca Ronchini, Ronchini, Francesca, Luca Comanducci +3
Arts and Humanities · Computer Science · #Audio and Speech Processing (eess.AS) #Diverse Musicological Studies #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Signal Processing (eess.SP) #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2403.17864
openalex publication_date 2024/03/26 · openalex created_date 2024/03/29 · openalex updated_date 2026/07/28
In recent years, text-to-audio models have revolutionized the field of automatic audio generation. This paper investigates their application in generating synthetic datasets for training data-driven models. Specifically, this study analyzes the performance of two environmental sound classification systems trained with data generated from text-to-audio models. We considered three scenarios: a) augmenting the training dataset with data generated by text-to-audio models; b) using a mixed training dataset combining real and synthetic text-driven generated data; and c) using a training dataset composed entirely of synthetic audio. In all cases, the performance of the classification models was tested on real data. Results indicate that text-to-audio models are effective for dataset augmentation, with consistent performance when replacing a subset of the recorded dataset. However, the performance of the audio recognition models drops when relying entirely on generated audio.