Deep neural networks for acoustic emotion recognition: Raising the benchmarks

  • Deep Neural Networks (DNNs) denote multilayer artificial neural networks with more than one hidden layer and millions of free parameters. We propose a Generalized Discriminant Analysis (GerDA) based on DNNs to learn discriminative features of low dimension optimized with respect to a fast classification from a large set of acoustic features for emotion recognition. On nine frequently used emotional speech corpora, we compare the performance of GerDA features and their subsequent linear classification with previously reported benchmarks obtained using the same set of acoustic features classified by Support Vector Machines (SVMs). Our results impressively show that low-dimensional GerDA features capture hidden information from the acoustic features leading to a significantly raised unweighted average recall and considerably raised weighted average recall.

Export metadata

Metadaten
Author:André StuhlsatzORCiDGND, Christine Meyer, Florian Eyben, Thomas Zielke, Gunter Meier, Bjorn Schuller
Fachbereich/Einrichtung:Hochschule Düsseldorf / Fachbereich - Maschinenbau und Verfahrenstechnik
Document Type:Conference Proceeding
Year of Completion:2011
Language of Publication:English
Publisher:IEEE
Parent Title (English):2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Page Number:4
First Page:5688
Last Page:5691
DOI:https://doi.org/10.1109/ICASSP.2011.5947651
Licence (German):keine Lizenz - nur Metadaten
Release Date:2025/07/16
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.