Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering

Yuanbo Hou; Qiuqiang Kong; Shengchen Li; Mark D. Plumbley

ICASSP 2019accepted0 citations

Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering

Yuanbo Hou, Qiuqiang Kong, Shengchen Li, Mark D. Plumbley

Abstract

Sound event detection (SED) methods typically rely on either strongly labelled data or weakly labelled data. As an alternative, sequentially labelled data (SLD) was proposed. In SLD, the events and the order of events in audio clips are known, without knowing the occurrence time of events. This paper proposes a connectionist temporal classification (CTC) based SED system that uses SLD instead of strongly labelled data, with a novel unsupervised clustering stage. Experiments on 41 classes of sound events show that the proposed two-stage method trained on SLD achieves performance comparable to the previous state-of-the-art SED system trained on strongly labelled data, and is far better than another state-of-the-art SED system trained on weakly labelled data, which indicates the effectiveness of the proposed two-stage method trained on SLD without any onset/offset time of sound events.

BibTeX

@inproceedings{icassp2019_soundeventdetect,
  title = {Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering},
  author = {Yuanbo Hou and Qiuqiang Kong and Shengchen Li and Mark D. Plumbley},
  booktitle = {ICASSP 2019},
  year = {2019}
}