Multi-task deep neural network with shared hidden layers: Breaking down the wall between emotion representations

Yue Zhang, Yifan Liu, Felix Weninger, Bjorn Schuller

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

50 Zitate (Scopus)

Abstract

Emotion representations are psychological constructs for modelling, analysing, and recognising emotion, being one essential element of affect. Due to its complexity, the boundaries between different emotion concepts are often fuzzy, which is also reflected in the diversification of emotion databases, and their inconsistent target labels. When facing data scarcity as an ever present issue for acoustic emotion recognition, the straightforward method to jointly use the existing data resources is to map various emotion labels onto one common dimensional space; this, however, comes with considerable information loss. To solve the dilemma of data aggregation whilst efficiently exploiting the emotion labels in terms of their original meaning and interrelations, we advocate the usage of multi-task deep neural networks with shared hidden layers (MT-SHL-DNN), in which the feature transformations are shared across different emotion representations, while the output layers are separately associated with each emotion database. On nine frequently used emotional speech corpora and two different acoustic feature sets, we demonstrate that the MT-SHL-DNN method outperforms the single-task DNNs trained with only one emotion representation.

OriginalspracheEnglisch
Titel2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten4990-4994
Seitenumfang5
ISBN (elektronisch)9781509041176
DOIs
PublikationsstatusVeröffentlicht - 16 Juni 2017
Extern publiziertJa
Veranstaltung2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, USA/Vereinigte Staaten
Dauer: 5 März 20179 März 2017

Publikationsreihe

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Konferenz

Konferenz2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Land/GebietUSA/Vereinigte Staaten
OrtNew Orleans
Zeitraum5/03/179/03/17

Fingerprint

Untersuchen Sie die Forschungsthemen von „Multi-task deep neural network with shared hidden layers: Breaking down the wall between emotion representations“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren