Opens in a new tab

AES E-Library

← Back to search

Journal Article

Applause Sound Detection

Authors: Uhle, Christian

Journal of the Audio Engineering Society · Volume 59 · Issue 4 · pp. 213–224 · April 2011

Abstract

Detecting applause in both audio recordings and real-time performances is relevant in such applications as music information retrieval and spatial audio coding. A combination of mel-frequency cepstral coefficients and low-level descriptors yielded the best classification performance in the experiments. Low-pass filtering of the feature time series leads to the concept of sigma features. Binary misclassification occurs more often when applause and nonapplause with similar amplitudes are simultaneously present.

Details

Publication
Journal of the Audio Engineering Society
Volume
59
Issue
4
Pages
213–224
Publication date
April 6, 2011
Affiliation
Fraunhofer Institute for Integrated Circuits, Erlangen, Germany (See document for exact affiliation information.)
Type
Journal Article