Acoustic features of anger utterances during natural dialog

Yoshiko Arimoto, Sumio Ohno, Hitoshi Iida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This report focuses on an automatic estimation of speakers' anger emotion degree. Two kinds of pseudo-dialogs were held to collect spontaneous anger utterances during the natural Japanese dialog. In order to quantify the anger degree of utterances, a six-scale subjective evaluation was conducted to grade every utterance according to an anger emotion degree by twelve evaluators. With this data set, acoustic features of each utterance were examined to clarify what is the clue to estimate degree of anger utterances. To examine the possibility of automatic emotion estimation, we conducted experiment to estimate the degree of anger emotion automatically by multiple regression analysis using the acoustic parameters.

Original languageEnglish
Title of host publicationInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Pages2556-2559
Number of pages4
Volume4
Publication statusPublished - 2007
Externally publishedYes
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, Belgium
Duration: 2007 Aug 272007 Aug 31

Other

Other8th Annual Conference of the International Speech Communication Association, Interspeech 2007
CountryBelgium
CityAntwerp
Period07/8/2707/8/31

Fingerprint

anger
acoustics
Acoustics
dialogue
emotion
Regression analysis
Experiments
regression analysis
experiment
evaluation

Keywords

  • Acoustic features
  • Emotional speech
  • Natural dialog

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Modelling and Simulation
  • Linguistics and Language
  • Communication

Cite this

Arimoto, Y., Ohno, S., & Iida, H. (2007). Acoustic features of anger utterances during natural dialog. In International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007 (Vol. 4, pp. 2556-2559)

Acoustic features of anger utterances during natural dialog. / Arimoto, Yoshiko; Ohno, Sumio; Iida, Hitoshi.

International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 4 2007. p. 2556-2559.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Arimoto, Y, Ohno, S & Iida, H 2007, Acoustic features of anger utterances during natural dialog. in International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. vol. 4, pp. 2556-2559, 8th Annual Conference of the International Speech Communication Association, Interspeech 2007, Antwerp, Belgium, 07/8/27.
Arimoto Y, Ohno S, Iida H. Acoustic features of anger utterances during natural dialog. In International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 4. 2007. p. 2556-2559
Arimoto, Yoshiko ; Ohno, Sumio ; Iida, Hitoshi. / Acoustic features of anger utterances during natural dialog. International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 4 2007. pp. 2556-2559
@inproceedings{57e0ae1536d34ec5bceee09887b57479,
title = "Acoustic features of anger utterances during natural dialog",
abstract = "This report focuses on an automatic estimation of speakers' anger emotion degree. Two kinds of pseudo-dialogs were held to collect spontaneous anger utterances during the natural Japanese dialog. In order to quantify the anger degree of utterances, a six-scale subjective evaluation was conducted to grade every utterance according to an anger emotion degree by twelve evaluators. With this data set, acoustic features of each utterance were examined to clarify what is the clue to estimate degree of anger utterances. To examine the possibility of automatic emotion estimation, we conducted experiment to estimate the degree of anger emotion automatically by multiple regression analysis using the acoustic parameters.",
keywords = "Acoustic features, Emotional speech, Natural dialog",
author = "Yoshiko Arimoto and Sumio Ohno and Hitoshi Iida",
year = "2007",
language = "English",
isbn = "9781605603162",
volume = "4",
pages = "2556--2559",
booktitle = "International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007",

}

TY - GEN

T1 - Acoustic features of anger utterances during natural dialog

AU - Arimoto, Yoshiko

AU - Ohno, Sumio

AU - Iida, Hitoshi

PY - 2007

Y1 - 2007

N2 - This report focuses on an automatic estimation of speakers' anger emotion degree. Two kinds of pseudo-dialogs were held to collect spontaneous anger utterances during the natural Japanese dialog. In order to quantify the anger degree of utterances, a six-scale subjective evaluation was conducted to grade every utterance according to an anger emotion degree by twelve evaluators. With this data set, acoustic features of each utterance were examined to clarify what is the clue to estimate degree of anger utterances. To examine the possibility of automatic emotion estimation, we conducted experiment to estimate the degree of anger emotion automatically by multiple regression analysis using the acoustic parameters.

AB - This report focuses on an automatic estimation of speakers' anger emotion degree. Two kinds of pseudo-dialogs were held to collect spontaneous anger utterances during the natural Japanese dialog. In order to quantify the anger degree of utterances, a six-scale subjective evaluation was conducted to grade every utterance according to an anger emotion degree by twelve evaluators. With this data set, acoustic features of each utterance were examined to clarify what is the clue to estimate degree of anger utterances. To examine the possibility of automatic emotion estimation, we conducted experiment to estimate the degree of anger emotion automatically by multiple regression analysis using the acoustic parameters.

KW - Acoustic features

KW - Emotional speech

KW - Natural dialog

UR - http://www.scopus.com/inward/record.url?scp=56149119878&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56149119878&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781605603162

VL - 4

SP - 2556

EP - 2559

BT - International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007

ER -