Artificial bandwidth extension to improve automatic emotion recognition from narrow-band coded speech

Albahri, A, Sandoval Rodriguez, C and Lech, M 2016, 'Artificial bandwidth extension to improve automatic emotion recognition from narrow-band coded speech', in Tadeusz A Wysocki and Beata J Wysocki (ed.) Proceedings of the 10th International Conference on Signal Processing and Communication Systems, (ICSPCS 2016), Gold Coast, Australia, 19-21 December 2016, pp. 1-7.


Document type: Conference Paper
Collection: Conference Papers

Title Artificial bandwidth extension to improve automatic emotion recognition from narrow-band coded speech
Author(s) Albahri, A
Sandoval Rodriguez, C
Lech, M
Year 2016
Conference name ICSPCS 2016
Conference location Gold Coast, Australia
Conference dates 19-21 December 2016
Proceedings title Proceedings of the 10th International Conference on Signal Processing and Communication Systems, (ICSPCS 2016)
Editor(s) Tadeusz A Wysocki and Beata J Wysocki
Publisher IEEE
Place of publication United States
Start page 1
End page 7
Total pages 7
Abstract Narrow-band speech coding techniques were previously found to reduce the accuracy of automatic Speech Emotion Recognition (SER), as well as speech and speaker recognition rates. Artificial Bandwidth Extension (ABE) based on spectral folding and spectral envelope estimation has been applied to compressed narrowband speech to test if an improvement in SER can be achieved. The modelling and classification of speech was performed with a benchmark approach based on the GMM classifier and a set of speech acoustic parameters including MFCCs, TEO and glottal parameters. The tests used the Berlin Emotional Speech data base. In general, ABE led to an improvement of SER accuracy; however the amount of improvement varied between different features, genders, and speech compression rates. In all cases, SER accuracy with ABE was at least 10% lower than for uncompressed speech.
Subjects Signal Processing
Keyword(s) speech classification
artificial bandwidth extension
speech emotion recognition
DOI - identifier 10.1109/ICSPCS.2016.7843305
Copyright notice © 2016 IEEE
ISBN 9781509009411
Versions
Version Filter Type
Altmetric details:
Access Statistics: 104 Abstract Views  -  Detailed Statistics
Created: Tue, 07 Mar 2017, 08:35:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us