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.
Werner, Johannes; Fritsch, Tobias
Affiliations: Hochschule Mittweida, Mittweida, Germany; Fraunhofer Institute for Digital Media Technology IDMT, Ilmenau, Germany(See document for exact affiliation information.)
AES Convention: 151 (October 2021) eBrief:650
Publication Date: October 13, 2021
No AES members have commented on this paper yet.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.