Show simple item record

dc.contributor.author
Deng, Jun
dc.contributor.author
Xu, Xinzhou
dc.contributor.author
Zhang, Zixing
dc.contributor.author
Frühholz, Sascha
dc.contributor.author
Schuller, Björn
dc.date.accessioned
2024-07-23T15:24:42Z
dc.date.available
2017-06-12T12:43:15Z
dc.date.available
2019-11-19T13:21:25Z
dc.date.available
2024-07-23T15:22:53Z
dc.date.available
2024-07-23T15:24:42Z
dc.date.issued
2016
dc.identifier.issn
2169-3536
dc.identifier.other
10.1109/access.2016.2591442
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/120647
dc.description.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.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
Phase-based features
en_US
dc.subject
Whispered speech emotion recognition
en_US
dc.subject
Outer product
en_US
dc.title
Exploitation of Phase-Based Features for Whispered Speech Emotion Recognition
en_US
dc.type
Journal Article
dc.date.published
2016-07-27
ethz.journal.title
IEEE Access
ethz.journal.volume
4
en_US
ethz.pages.start
4299
en_US
ethz.pages.end
4309
en_US
ethz.identifier.wos
ethz.identifier.nebis
009976867
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2017-06-12T12:45:48Z
ethz.source
ECIT
ethz.identifier.importid
imp593654b7908c854386
ethz.ecitpid
pub:182721
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2017-07-18T08:42:59Z
ethz.rosetta.lastUpdated
2020-02-15T22:40:30Z
ethz.rosetta.exportRequired
true
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Exploitation%20of%20Phase-Based%20Features%20for%20Whispered%20Speech%20Emotion%20Recognition&rft.jtitle=IEEE%20Access&rft.date=2016&rft.volume=4&rft.spage=4299&rft.epage=4309&rft.issn=2169-3536&rft.au=Deng,%20Jun&Xu,%20Xinzhou&Zhang,%20Zixing&Fr%C3%BChholz,%20Sascha&Schuller,%20Bj%C3%B6rn&rft.genre=article&rft_id=info:doi/10.1109/access.2016.2591442&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record