Learning to Match Transient Sound Events Using Attentional Similarity for Few-shot Sound Recognition
Authors:
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 26-30
Abstract
In this paper, we introduce a novel attentional similarity module for the problem of few-shot sound recognition. Given a few examples of an unseen sound event, a classifier must be quickly adapted to recognize the new sound event without much fine-tuning. The proposed attentional similarity module can be plugged into any metric-based learning method for few-shot learning, allowing the resulting model to especially match related short sound events. Extensive experiments on two datasets show that the proposed module consistently improves the performance of five different metric-based learning methods for few-shot sound recognition. The relative improvement ranges from +4.1% to +7.7% for 5-shot 5-way accuracy for the ESC-50 dataset, and from +2.1% to +6.5% for noiseESC-50. Qualitative results demonstrate that our method contributes in particular to the recognition of transient sound events.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Learning to Recognize Transient Sound Events using Attentional Supervision2018
- Knowledge Transfer from Weakly Labeled Audio Using Convolutional Neural Network for Sound Events and Scenes2018
- Weakly-supervised audio event detection using event-specific Gaussian filters and fully convolutional networks2017
- Audio Set: An ontology and human-labeled dataset for audio events2017
- CNN architectures for large-scale audio classification2017
- TUT database for acoustic scene classification and sound event detection2016
- Deep Residual Learning for Image Recognition2016
- Learning Deep Representation for Imbalanced Classification2016
- ESC2015
- librosa: Audio and Music Signal Analysis in Python2015