Exploitation of Phase-Based Features for Whispered Speech Emotion Recognition
OPEN ACCESS
Loading...
Author / Producer
Date
2016
Publication Type
Journal Article
ETH Bibliography
yes
OPEN ACCESS
Data
Rights / License
Abstract
Features for speech emotion recognition are usually dominated by the spectral magnitude information while they ignore the use of the phase spectrum because of the difficulty of properly interpreting it. Motivated by recent successes of phase-based features for speech processing, this paper investigates the effectiveness of phase information for whispered speech emotion recognition. We select two types of phase-based features (i.e., modified group delay features and all-pole group delay features), both which have shown wide applicability to all sorts of different speech analysis and are now studied in whispered speech emotion recognition. When exploiting these features, we propose a new speech emotion recognition framework, employing outer product in combination with power and L2 normalization. The according technique encodes any variable length sequence of the phase-based features into a fixed dimension vector regardless of the length of the input sequence. The resulting representation is fed to train a classification model with a linear kernel classifier. Experimental results on the Geneva Whispered Emotion Corpus database, including normal and whispered phonation, demonstrate the effectiveness of the proposed method when compared with other modern systems. It is also shown that, combining phase information with magnitude information could significantly improve performance over the common systems solely adopting magnitude information.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
4
Pages / Article No.
4299 - 4309
Publisher
IEEE
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Phase-based features; Whispered speech emotion recognition; Outer product