Analysis of excitation source features of speech for emotion recognition

Sudarsana Reddy Kadiri; P. Gangamohan; Suryakanth V. Gangashetty; B. Yegnanarayana

Analysis of excitation source features of speech for emotion recognition

Sudarsana Reddy Kadiri, P. Gangamohan, Suryakanth V. Gangashetty, B. Yegnanarayana

Not published at Aalto University

International Institute of Information Technology Hyderabad

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

50 Citations (Scopus)

Abstract

During production of emotional speech there are deviations in the components of speech production mechanism when compared to normal speech. The objective of this study is to capture the deviations in features related to the excitation source component of speech, and to develop a system for automatic recognition of emotions based on these deviations. The emotions considered for this study are: Anger, happy, neutral and sad. The study shows that there are useful features in the deviations of the excitation source features at subsegmental level, and they can be exploited to develop an emotion recognition system. A hierarchical binary decision tree approach is used for classification.

Original language	English
Title of host publication	Interspeech
Publisher	International Speech Communication Association (ISCA)
Pages	1324-1328
Number of pages	5
Volume	2015-January
Publication status	Published - 2015
MoE publication type	A4 Conference publication
Event	Interspeech - Dresden, Germany Duration: 6 Sept 2015 → 10 Sept 2015 Conference number: 16

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association
Publisher	International Speech Communication Association
ISSN (Print)	2308-457X

Conference

Conference	Interspeech
Country/Territory	Germany
City	Dresden
Period	06/09/2015 → 10/09/2015

Keywords

Emotion recognition
Kullback-Leibler distance
Linear prediction analysis
Zero frequency filtering

Cite this

@inproceedings{56eb5e57a71a4669a999da21348864ec,

title = "Analysis of excitation source features of speech for emotion recognition",

abstract = "During production of emotional speech there are deviations in the components of speech production mechanism when compared to normal speech. The objective of this study is to capture the deviations in features related to the excitation source component of speech, and to develop a system for automatic recognition of emotions based on these deviations. The emotions considered for this study are: Anger, happy, neutral and sad. The study shows that there are useful features in the deviations of the excitation source features at subsegmental level, and they can be exploited to develop an emotion recognition system. A hierarchical binary decision tree approach is used for classification.",

keywords = "Emotion recognition, Kullback-Leibler distance, Linear prediction analysis, Zero frequency filtering",

author = "Kadiri, {Sudarsana Reddy} and P. Gangamohan and Gangashetty, {Suryakanth V.} and B. Yegnanarayana",

note = "Publisher Copyright: Copyright {\textcopyright} 2015 ISCA.; Interspeech ; Conference date: 06-09-2015 Through 10-09-2015",

year = "2015",

language = "English",

volume = "2015-January",

series = "Proceedings of the Annual Conference of the International Speech Communication Association",

publisher = "International Speech Communication Association (ISCA)",

pages = "1324--1328",

booktitle = "Interspeech",

address = "France",

}

Kadiri, SR, Gangamohan, P, Gangashetty, SV & Yegnanarayana, B 2015, Analysis of excitation source features of speech for emotion recognition. in Interspeech. vol. 2015-January, Proceedings of the Annual Conference of the International Speech Communication Association, International Speech Communication Association (ISCA), pp. 1324-1328, Interspeech, Dresden, Germany, 06/09/2015.

Analysis of excitation source features of speech for emotion recognition. / Kadiri, Sudarsana Reddy; Gangamohan, P.; Gangashetty, Suryakanth V. et al.
Interspeech. Vol. 2015-January International Speech Communication Association (ISCA), 2015. p. 1324-1328 (Proceedings of the Annual Conference of the International Speech Communication Association).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Analysis of excitation source features of speech for emotion recognition

AU - Kadiri, Sudarsana Reddy

AU - Gangamohan, P.

AU - Gangashetty, Suryakanth V.

AU - Yegnanarayana, B.

N1 - Conference code: 16

PY - 2015

Y1 - 2015

N2 - During production of emotional speech there are deviations in the components of speech production mechanism when compared to normal speech. The objective of this study is to capture the deviations in features related to the excitation source component of speech, and to develop a system for automatic recognition of emotions based on these deviations. The emotions considered for this study are: Anger, happy, neutral and sad. The study shows that there are useful features in the deviations of the excitation source features at subsegmental level, and they can be exploited to develop an emotion recognition system. A hierarchical binary decision tree approach is used for classification.

AB - During production of emotional speech there are deviations in the components of speech production mechanism when compared to normal speech. The objective of this study is to capture the deviations in features related to the excitation source component of speech, and to develop a system for automatic recognition of emotions based on these deviations. The emotions considered for this study are: Anger, happy, neutral and sad. The study shows that there are useful features in the deviations of the excitation source features at subsegmental level, and they can be exploited to develop an emotion recognition system. A hierarchical binary decision tree approach is used for classification.

KW - Emotion recognition

KW - Kullback-Leibler distance

KW - Linear prediction analysis

KW - Zero frequency filtering

UR - http://www.scopus.com/inward/record.url?scp=84959099391&partnerID=8YFLogxK

M3 - Conference article in proceedings

AN - SCOPUS:84959099391

VL - 2015-January

T3 - Proceedings of the Annual Conference of the International Speech Communication Association

SP - 1324

EP - 1328

BT - Interspeech

PB - International Speech Communication Association (ISCA)

T2 - Interspeech

Y2 - 6 September 2015 through 10 September 2015

ER -

Analysis of excitation source features of speech for emotion recognition

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this