Semisupervised Autoencoders for Speech Emotion Recognition

Despite the widespread use of supervised learning methods for speech emotion recognition, they are severely restricted due to the lack of sufficient amount of labelled speech data for the training. Considering the wide availability of unlabelled speech data, therefore, this paper proposes semisuperv...

Full description

Saved in:
Bibliographic Details
Published inIEEE/ACM transactions on audio, speech, and language processing Vol. 26; no. 1; pp. 31 - 43
Main Authors Jun Deng, Xinzhou Xu, Zixing Zhang, Fruhholz, Sascha, Schuller, Bjorn
Format Journal Article
LanguageEnglish
Published IEEE 01.01.2018
Subjects
Autoencoders
Emotion recognition
semi-supervised learning
Semisupervised learning
Speech
speech emotion recognition
Speech processing
Speech recognition
Supervised learning
Training
Online AccessGet full text

Cover

More Information
Summary:Despite the widespread use of supervised learning methods for speech emotion recognition, they are severely restricted due to the lack of sufficient amount of labelled speech data for the training. Considering the wide availability of unlabelled speech data, therefore, this paper proposes semisupervised autoencoders to improve speech emotion recognition. The aim is to reap the benefit from the combination of the labelled data and unlabelled data. The proposed model extends a popular unsupervised autoencoder by carefully adjoining a supervised learning objective. We extensively evaluate the proposed model on the INTERSPEECH 2009 Emotion Challenge database and other four public databases in different scenarios. Experimental results demonstrate that the proposed model achieves state-of-the-art performance with a very small number of labelled data on the challenge task and other tasks, and significantly outperforms other alternative methods.
ISSN:2329-9290
2329-9304
DOI:10.1109/TASLP.2017.2759338