Tampere University of Technology

TUTCRIS Research Portal

An active learning method using clustering and committee-based sample selection for sound event classification

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication16th International Workshop on Acoustic Signal Enhancement, IWAENC 2018
PublisherIEEE
Pages116-120
Number of pages5
ISBN (Electronic)9781538681510
DOIs
Publication statusPublished - 2 Nov 2018
Publication typeA4 Article in a conference publication
EventInternational Workshop on Acoustic Signal Enhancement - Tokyo, Japan
Duration: 17 Sep 201820 Sep 2018

Conference

ConferenceInternational Workshop on Acoustic Signal Enhancement
CountryJapan
CityTokyo
Period17/09/1820/09/18

Abstract

This paper proposes an active learning method to control a labeling process for efficient annotation of acoustic training material, which is used for training sound event classifiers. The proposed method performs K-medoids clustering over an initially unlabeled dataset, and medoids as local representatives, are presented to an annotator for manual annotation. The annotated label on a medoid propagates to other samples in its cluster for label prediction. After annotating the medoids, the annotation continues to the unexamined sounds with mismatched prediction results from two classifiers, a nearest-neighbor classifier and a model-based classifier, both trained with annotated data. The annotation on the segments with mismatched predictions are ordered by the distance to the nearest annotated sample, farthest first. The evaluation is made on a public environmental sound dataset. The labels obtained through a labeling process controlled by the proposed method are used to train a classifier, using supervised learning. Only 20% of the data needs to be manually annotated with the proposed method, to achieve the accuracy with all the data annotated. In addition, the proposed method clearly outperforms other active learning algorithms proposed for sound event classification through all the experiments, simulating varying fraction of data that is manually labeled.

Keywords

  • Active learning, Committee-based sample selection, K-medoids clustering, Sound event classification

Publication forum classification

Field of science, Statistics Finland