Head pose estimation and motion analysis of public speaking videos

Rinko Komiya, Takeshi Saitoh, Miharu Fuyuno, Yuko Yamashita, Yoshitaka Nakajima

Research output: Contribution to journalArticle

Abstract

Public speaking is an essential skill in a large variety of professions and also in everyday life. However, it can be difficult to master. This paper focuses on the automatic assessment of nonverbal facial behavior during public speaking and proposes simple and efficient methods of head pose estimation and motion analysis. The authors collected nine and six speech videos from a recitation and oration contest, respectively, conducted at a Japanese high school and applied the proposed method to evaluate the contestants' performance. For the estimation of head pose from speech videos, their method produced results with an acceptable level of accuracy. The proposed motion analysis method can be used for calculating frequencies and moving ranges of head motion. The authors found that the proposed parameters and the eye-contact score are strongly correlated and that the proposed frequency and moving range parameters are suitable for evaluating public speaking. Thus, on the basis of these features, a teacher can provide accurate feedback to help a speaker improve.

LanguageEnglish
Pages57-71
Number of pages15
JournalInternational Journal of Software Innovation
Volume5
Issue number1
DOIs
StatePublished - 2017 Jan 1

Fingerprint

Feedback
Motion analysis

Keywords

  • English Oration Contest
  • English Recitation Contest
  • Facial Feature Point
  • Head Pose Estimation
  • Image Processing
  • Motion Analysis
  • Speech Video

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Computer Science Applications
  • Software

Cite this

Head pose estimation and motion analysis of public speaking videos. / Komiya, Rinko; Saitoh, Takeshi; Fuyuno, Miharu; Yamashita, Yuko; Nakajima, Yoshitaka.

In: International Journal of Software Innovation, Vol. 5, No. 1, 01.01.2017, p. 57-71.

Research output: Contribution to journalArticle

Komiya, Rinko ; Saitoh, Takeshi ; Fuyuno, Miharu ; Yamashita, Yuko ; Nakajima, Yoshitaka. / Head pose estimation and motion analysis of public speaking videos. In: International Journal of Software Innovation. 2017 ; Vol. 5, No. 1. pp. 57-71
@article{18bbfb2183ba4c5aae868b4434cbf969,
title = "Head pose estimation and motion analysis of public speaking videos",
abstract = "Public speaking is an essential skill in a large variety of professions and also in everyday life. However, it can be difficult to master. This paper focuses on the automatic assessment of nonverbal facial behavior during public speaking and proposes simple and efficient methods of head pose estimation and motion analysis. The authors collected nine and six speech videos from a recitation and oration contest, respectively, conducted at a Japanese high school and applied the proposed method to evaluate the contestants' performance. For the estimation of head pose from speech videos, their method produced results with an acceptable level of accuracy. The proposed motion analysis method can be used for calculating frequencies and moving ranges of head motion. The authors found that the proposed parameters and the eye-contact score are strongly correlated and that the proposed frequency and moving range parameters are suitable for evaluating public speaking. Thus, on the basis of these features, a teacher can provide accurate feedback to help a speaker improve.",
keywords = "English Oration Contest, English Recitation Contest, Facial Feature Point, Head Pose Estimation, Image Processing, Motion Analysis, Speech Video",
author = "Rinko Komiya and Takeshi Saitoh and Miharu Fuyuno and Yuko Yamashita and Yoshitaka Nakajima",
year = "2017",
month = "1",
day = "1",
doi = "10.4018/IJSI.2017010105",
language = "English",
volume = "5",
pages = "57--71",
journal = "International Journal of Software Innovation",
issn = "2166-7160",
publisher = "IGI Global Publishing",
number = "1",

}

TY - JOUR

T1 - Head pose estimation and motion analysis of public speaking videos

AU - Komiya,Rinko

AU - Saitoh,Takeshi

AU - Fuyuno,Miharu

AU - Yamashita,Yuko

AU - Nakajima,Yoshitaka

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Public speaking is an essential skill in a large variety of professions and also in everyday life. However, it can be difficult to master. This paper focuses on the automatic assessment of nonverbal facial behavior during public speaking and proposes simple and efficient methods of head pose estimation and motion analysis. The authors collected nine and six speech videos from a recitation and oration contest, respectively, conducted at a Japanese high school and applied the proposed method to evaluate the contestants' performance. For the estimation of head pose from speech videos, their method produced results with an acceptable level of accuracy. The proposed motion analysis method can be used for calculating frequencies and moving ranges of head motion. The authors found that the proposed parameters and the eye-contact score are strongly correlated and that the proposed frequency and moving range parameters are suitable for evaluating public speaking. Thus, on the basis of these features, a teacher can provide accurate feedback to help a speaker improve.

AB - Public speaking is an essential skill in a large variety of professions and also in everyday life. However, it can be difficult to master. This paper focuses on the automatic assessment of nonverbal facial behavior during public speaking and proposes simple and efficient methods of head pose estimation and motion analysis. The authors collected nine and six speech videos from a recitation and oration contest, respectively, conducted at a Japanese high school and applied the proposed method to evaluate the contestants' performance. For the estimation of head pose from speech videos, their method produced results with an acceptable level of accuracy. The proposed motion analysis method can be used for calculating frequencies and moving ranges of head motion. The authors found that the proposed parameters and the eye-contact score are strongly correlated and that the proposed frequency and moving range parameters are suitable for evaluating public speaking. Thus, on the basis of these features, a teacher can provide accurate feedback to help a speaker improve.

KW - English Oration Contest

KW - English Recitation Contest

KW - Facial Feature Point

KW - Head Pose Estimation

KW - Image Processing

KW - Motion Analysis

KW - Speech Video

UR - http://www.scopus.com/inward/record.url?scp=85024120529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024120529&partnerID=8YFLogxK

U2 - 10.4018/IJSI.2017010105

DO - 10.4018/IJSI.2017010105

M3 - Article

VL - 5

SP - 57

EP - 71

JO - International Journal of Software Innovation

T2 - International Journal of Software Innovation

JF - International Journal of Software Innovation

SN - 2166-7160

IS - 1

ER -