Comparison of Regression and Classification Models for Multi-Source Direction of Arrival Estimation with Convolutional Recurrent Neural Networks (en)

* Presenting author
Day / Time: 09.03.2023, 11:00-11:40
Typ: Poster
Information: Die Poster werden durchgängig von Dienstag bis Donnerstag im Foyer auf Ebene Z ausgestellt (3.OG vor dem Plenarsaal Z), sortiert nach thematischen Zusammenhängen in der hier angegebenen Posterinsel (siehe Sitzungstitel). Das Posterforum zur angegebenen Zeit bietet die Möglichkeit, mit den Autor*innen in Diskussion zu kommen.
Abstract: Direction of arrival estimation using deep learning is a well-established research area, usually approached as a regression or classification model. While classification methods have been used preferentially for some time especially for multi-source localization, regression methods have become increasingly popular due to their ability to provide continuous direction estimation. However, multi-source regression is a challenging problem as it requires addressing the issue of permutation invariance.Regression and classification approaches have already been compared in detail for single-source localization. For multi-source localization, there are numerous proposed methods in both categories, but, to the best of our knowledge, there is no systematic comparison between the two options. In this study, we aim to fill this gap by providing a comprehensive analysis of regression and classification models, especially in multi-source localization scenarios.


strpos(): Passing null to parameter #1 ($haystack) of type string is deprecated

/kunden/431424_13355/webseiten/subdomains/, line 35
32.              */
33.             if (headers_sent()) {
34.                 $encoding = false;
35.             } elseif (strpos($HTTP_ACCEPT_ENCODING, 'x-gzip') !== false) {
36.                 $encoding = 'x-gzip';
37.             } elseif (strpos($HTTP_ACCEPT_ENCODING, 'gzip') !== false) {
38.                 $encoding = 'gzip';