English

SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer

Audio and Speech Processing 2025-01-03 v2 Sound

Abstract

In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound events. We evaluate this approach on the FSD Kaggle 2018 mixture dataset and real data from AudioSet, where SoloAudio achieves the state-of-the-art results on both in-domain and out-of-domain data, and exhibits impressive zero-shot and few-shot capabilities. Source code and demos are released.

Keywords

Cite

@article{arxiv.2409.08425,
  title  = {SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer},
  author = {Helin Wang and Jiarui Hai and Yen-Ju Lu and Karan Thakkar and Mounya Elhilali and Najim Dehak},
  journal= {arXiv preprint arXiv:2409.08425},
  year   = {2025}
}

Comments

Submitted to ICASSP 2025

R2 v1 2026-06-28T18:43:06.513Z