Header

UZH-Logo

Maintenance Infos

Universum autoencoder-based domain adaptation for speech emotion recognition


Deng, Jun; Xu, Xinzhou; Zhang, Zixing; Frühholz, Sascha; Schuller, Bjorn (2017). Universum autoencoder-based domain adaptation for speech emotion recognition. IEEE Signal Processing Letters, 24(4):500-504.

Abstract

One of the serious obstacles to the applications of speech emotion recognition systems in real-life settings is the lack of generalization of the emotion classifiers. Many recognition systems often present a dramatic drop in performance when tested on speech data obtained from different speakers, acoustic environments, linguistic content, and domain conditions. In this letter, we propose a novel unsupervised domain adaptation model, called Universum autoencoders, to improve the performance of the systems evaluated in mismatched training and test conditions. To address the mismatch, our proposed model not only learns discriminative information from labeled data, but also learns to incorporate the prior knowledge from unlabeled data into the learning. Experimental results on the labeled Geneva Whispered Emotion Corpus database plus other three unlabeled databases demonstrate the effectiveness of the proposed method when compared to other domain adaptation methods.

Abstract

One of the serious obstacles to the applications of speech emotion recognition systems in real-life settings is the lack of generalization of the emotion classifiers. Many recognition systems often present a dramatic drop in performance when tested on speech data obtained from different speakers, acoustic environments, linguistic content, and domain conditions. In this letter, we propose a novel unsupervised domain adaptation model, called Universum autoencoders, to improve the performance of the systems evaluated in mismatched training and test conditions. To address the mismatch, our proposed model not only learns discriminative information from labeled data, but also learns to incorporate the prior knowledge from unlabeled data into the learning. Experimental results on the labeled Geneva Whispered Emotion Corpus database plus other three unlabeled databases demonstrate the effectiveness of the proposed method when compared to other domain adaptation methods.

Statistics

Citations

Dimensions.ai Metrics
2 citations in Web of Science®
2 citations in Scopus®
Google Scholar™

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Psychology
Dewey Decimal Classification:150 Psychology
Language:English
Date:April 2017
Deposited On:27 Nov 2017 10:06
Last Modified:14 Feb 2018 10:09
Publisher:Institute of Electrical and Electronics Engineers
ISSN:1070-9908
Publisher DOI:https://doi.org/10.1109/LSP.2017.2672753

Download

Full text not available from this repository.
View at publisher