Towards Affect Recognition: an Ica Approach

Abstract

The speech signal can be thought of as multi-spatial signal where each signal subspace corresponds to different attributes that affect the speech. Language, accent, speaker, emotions are few potential sub-spaces. Each space can further be projected into n-dimensions, as there are different languages, accents and emotions, which combine together to make… (More)

Topics

8 Figures and Tables

Cite this paper

@inproceedings{Rahurkar2003TowardsAR, title={Towards Affect Recognition: an Ica Approach}, author={Mandar Rahurkar}, year={2003} }