English

RaDur: A Reference-aware and Duration-robust Network for Target Sound Detection

Sound 2022-04-06 v1 Audio and Speech Processing

Abstract

Target sound detection (TSD) aims to detect the target sound from a mixture audio given the reference information. Previous methods use a conditional network to extract a sound-discriminative embedding from the reference audio, and then use it to detect the target sound from the mixture audio. However, the network performs much differently when using different reference audios (e.g. performs poorly for noisy and short-duration reference audios), and tends to make wrong decisions for transient events (i.e. shorter than 11 second). To overcome these problems, in this paper, we present a reference-aware and duration-robust network (RaDur) for TSD. More specifically, in order to make the network more aware of the reference information, we propose an embedding enhancement module to take into account the mixture audio while generating the embedding, and apply the attention pooling to enhance the features of target sound-related frames and weaken the features of noisy frames. In addition, a duration-robust focal loss is proposed to help model different-duration events. To evaluate our method, we build two TSD datasets based on UrbanSound and Audioset. Extensive experiments show the effectiveness of our methods.

Keywords

Cite

@article{arxiv.2204.02143,
  title  = {RaDur: A Reference-aware and Duration-robust Network for Target Sound Detection},
  author = {Dongchao Yang and Helin Wang and Zhongjie Ye and Yuexian Zou and Wenwu Wang},
  journal= {arXiv preprint arXiv:2204.02143},
  year   = {2022}
}

Comments

submitted to interspeech2022

R2 v1 2026-06-24T10:38:21.488Z