Connectionist Temporal Localization for Sound Event Detection with Sequential Labeling
Authors:
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 745-749
Abstract
Research on sound event detection (SED) with weak labeling has mostly focused on presence/absence labeling, which provides no temporal information at all about the event occurrences. In this paper, we consider SED with sequential labeling, which specifies the temporal order of the event boundaries. The conventional connectionist temporal classification (CTC) framework, when applied to SED with sequential labeling, does not localize long events well due to a "peak clustering" problem. We adapt the CTC framework and propose connectionist temporal localization (CTL), which successfully solves the problem. Evaluation on a subset of Audio Set shows that CTL closes a third of the gap between presence/ absence labeling and strong labeling, demonstrating the usefulness of the extra temporal information in sequential labeling. CTL also makes it easy to combine sequential labeling with presence/absence labeling and strong labeling.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Audio Set Classification with Attention Model: A Probabilistic Perspective2018
- A first attempt at polyphonic sound event detection using connectionist temporal classification2017
- Audio Set: An ontology and human-labeled dataset for audio events2017
- CNN architectures for large-scale audio classification2017
- XSEDE: Accelerating Scientific DiscoveryComputing in Science & Engineering, 2014
- Connectionist temporal classification2006