Opens in a new tab

AES E-Library

← Back to search

Engineering Brief

Automatic Classification of Enclosure-Types for Electrodynamic Loudspeakers

Authors: Werner, Johannes; Fritsch, Tobias

AES Convention 151 · Paper 650 · October 2021

Abstract

This article deals with the realization of an automated classification of loudspeaker enclosures. The acoustic load of the enclosure is reflected in the electrical impedance of the loudspeaker and is hence detectable from the point of view of the power amplifier. In order to classify the enclosures of passive one-way speakers, an artificial neural network is trained with synthetic impedance spectra based on equivalent electrical circuit models. The generalization capability is validated with measured test sets of closed, vented, band-pass and transmission-line enclosures. The resulting classification procedure works well within a synthetic test set. However, a good generalization to the measured test data requires further investigations to achieve better separation between the different vented enclosure types.

Details

Published in
AES Convention 151
AES Convention
151
Paper number
650
Publication date
October 6, 2021
Session subject
Transducers
Affiliation
Hochschule Mittweida, Mittweida, Germany; Fraunhofer Institute for Digital Media Technology IDMT, Ilmenau, Germany (See document for exact affiliation information.)
Type
Engineering Brief