Conference proceeding
Self-Training for Sound Event Detection in Audio Mixtures
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), v 2021-, pp 341-345
06 Jun 2021
Abstract
Sound event detection (SED) takes on the task of identifying presence of specific sound events in a complex audio recording. SED has tremendous implications in video analytics, smart speaker algorithms and audio tagging. Recent advances in deep learning have afforded remarkable advances in performance of SED systems; albeit at the cost of extensive labeling efforts to train supervised methods using fully described sound class labels and timestamps. In order to address limitations in availability of training data, this work proposes a self-training technique to leverage unlabeled datasets in supervised learning using pseudo label estimation. This approach proposes a dual-term objective function: a classification loss for the original labels and expectation loss for pseudo labels. The proposed self training technique is applied to sound event detection in the context of the DCASE 2020 challenge, and reports a notable improvement over the baseline system for this task. The self-training approach is particularly effective in extending the labeled database with concurrent sound events.
Metrics
Details
- Title
- Self-Training for Sound Event Detection in Audio Mixtures
- Creators
- Sangwook Park - Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USAAshwin Bellur - Johns Hopkins UniversityDavid K. Han - Drexel UniversityMounya Elhilali - Johns Hopkins UniversityIEEE
- Publication Details
- ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), v 2021-, pp 341-345
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000704288400069
- Scopus ID
- 2-s2.0-85115184815
- Other Identifier
- 991019169542804721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Acoustics
- Computer Science, Artificial Intelligence
- Computer Science, Software Engineering
- Engineering, Electrical & Electronic
- Imaging Science & Photographic Technology