Sparse Autoencoder-Based Feature Transfer Learning for Speech Emotion Recognition

In speech emotion recognition, training and test data used for system development usually tend to fit each other perfectly, but further 'similar' data may be available. Transfer learning helps to exploit such similar data for training despite the inherent dissimilarities in order to boost...

Full description

Saved in:
Bibliographic Details
Published inInternational Conference on Affective Computing and Intelligent Interaction and workshops pp. 511 - 516
Main Authors Jun Deng, Zixing Zhang, Marchi, Erik, Schuller, Bjorn
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2013
Subjects
Acoustics
deep neural networks
Emotion recognition
sparse autoencoder
Speech
speech emotion recognition
Speech recognition
Training
transfer learning
Online AccessGet full text

Cover

More Information
Summary:In speech emotion recognition, training and test data used for system development usually tend to fit each other perfectly, but further 'similar' data may be available. Transfer learning helps to exploit such similar data for training despite the inherent dissimilarities in order to boost a recogniser's performance. In this context, this paper presents a sparse auto encoder method for feature transfer learning for speech emotion recognition. In our proposed method, a common emotion-specific mapping rule is learnt from a small set of labelled data in a target domain. Then, newly reconstructed data are obtained by applying this rule on the emotion-specific data in a different domain. The experimental results evaluated on six standard databases show that our approach significantly improves the performance relative to learning each source domain independently.
ISSN:2156-8103
DOI:10.1109/ACII.2013.90