Detection and Analysis of Emotion from Speech Signals

Assel Davletcharova, Sherin Sugathan, Bibia Abraham, Alex Pappachen James

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Recognizing emotion from speech has become one the active research themes in speech processing and in applications based on human-computer interaction. This paper conducts an experimental study on recognizing emotions from human speech. The emotions considered for the experiments include neutral, anger, joy and sadness. The distinuishability of emotional features in speech were studied first followed by emotion classification performed on a custom dataset. The classification was performed for different classifiers. One of the main feature attribute considered in the prepared dataset was the peak-to-peak distance obtained from the graphical representation of the speech signals. After performing the classification tests on a dataset formed from 30 different subjects, it was found that for getting better accuracy, one should consider the data collected from one person rather than considering the data from a group of people.

Original languageEnglish
Pages (from-to)91-96
Number of pages6
JournalUnknown Journal
Volume58
DOIs
Publication statusPublished - 2015

Fingerprint

Speech processing
Human computer interaction
Classifiers
Experiments

Keywords

  • Emotion Analysis
  • Emotion Classification
  • Mel-Frequency Cepstral Coefficients
  • Speech Processing

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Detection and Analysis of Emotion from Speech Signals. / Davletcharova, Assel; Sugathan, Sherin; Abraham, Bibia; James, Alex Pappachen.

In: Unknown Journal, Vol. 58, 2015, p. 91-96.

Research output: Contribution to journalArticle

Davletcharova, Assel ; Sugathan, Sherin ; Abraham, Bibia ; James, Alex Pappachen. / Detection and Analysis of Emotion from Speech Signals. In: Unknown Journal. 2015 ; Vol. 58. pp. 91-96.
@article{c4fd1ef5f1484d2cb056cc34e0c962c1,
title = "Detection and Analysis of Emotion from Speech Signals",
abstract = "Recognizing emotion from speech has become one the active research themes in speech processing and in applications based on human-computer interaction. This paper conducts an experimental study on recognizing emotions from human speech. The emotions considered for the experiments include neutral, anger, joy and sadness. The distinuishability of emotional features in speech were studied first followed by emotion classification performed on a custom dataset. The classification was performed for different classifiers. One of the main feature attribute considered in the prepared dataset was the peak-to-peak distance obtained from the graphical representation of the speech signals. After performing the classification tests on a dataset formed from 30 different subjects, it was found that for getting better accuracy, one should consider the data collected from one person rather than considering the data from a group of people.",
keywords = "Emotion Analysis, Emotion Classification, Mel-Frequency Cepstral Coefficients, Speech Processing",
author = "Assel Davletcharova and Sherin Sugathan and Bibia Abraham and James, {Alex Pappachen}",
year = "2015",
doi = "10.1016/j.procs.2015.08.032",
language = "English",
volume = "58",
pages = "91--96",
journal = "Unknown Journal",

}

TY - JOUR

T1 - Detection and Analysis of Emotion from Speech Signals

AU - Davletcharova, Assel

AU - Sugathan, Sherin

AU - Abraham, Bibia

AU - James, Alex Pappachen

PY - 2015

Y1 - 2015

N2 - Recognizing emotion from speech has become one the active research themes in speech processing and in applications based on human-computer interaction. This paper conducts an experimental study on recognizing emotions from human speech. The emotions considered for the experiments include neutral, anger, joy and sadness. The distinuishability of emotional features in speech were studied first followed by emotion classification performed on a custom dataset. The classification was performed for different classifiers. One of the main feature attribute considered in the prepared dataset was the peak-to-peak distance obtained from the graphical representation of the speech signals. After performing the classification tests on a dataset formed from 30 different subjects, it was found that for getting better accuracy, one should consider the data collected from one person rather than considering the data from a group of people.

AB - Recognizing emotion from speech has become one the active research themes in speech processing and in applications based on human-computer interaction. This paper conducts an experimental study on recognizing emotions from human speech. The emotions considered for the experiments include neutral, anger, joy and sadness. The distinuishability of emotional features in speech were studied first followed by emotion classification performed on a custom dataset. The classification was performed for different classifiers. One of the main feature attribute considered in the prepared dataset was the peak-to-peak distance obtained from the graphical representation of the speech signals. After performing the classification tests on a dataset formed from 30 different subjects, it was found that for getting better accuracy, one should consider the data collected from one person rather than considering the data from a group of people.

KW - Emotion Analysis

KW - Emotion Classification

KW - Mel-Frequency Cepstral Coefficients

KW - Speech Processing

UR - http://www.scopus.com/inward/record.url?scp=84970978774&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84970978774&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2015.08.032

DO - 10.1016/j.procs.2015.08.032

M3 - Article

VL - 58

SP - 91

EP - 96

JO - Unknown Journal

JF - Unknown Journal

ER -