Cardiff conversation database (CCDB): A database of natural dyadic conversations

Andrew J. Aubrey; David Marshall; Paul L. Rosin; Jason Vendeventer; Douglas W. Cunningham; Christian Wallraven

doi:10.1109/CVPRW.2013.48

Cardiff conversation database (CCDB): A database of natural dyadic conversations

Andrew J. Aubrey, David Marshall, Paul L. Rosin, Jason Vendeventer, Douglas W. Cunningham, Christian Wallraven

Department of Brain and Cognitive Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

15 Citations (Scopus)

Abstract

We present the Cardiff Conversation Database (CCDb), a unique 2D audiovisual database containing natural conversations between pairs of people. The database currently contains 30 conversations. To date, eight conversations are fully annotated for speaker activity, facial expressions, head motion, and non-verbal utterances. In this paper we describe the data collection and annotation process. We also provide results of baseline experiments in which an SVM classifier was used to identify which parts of the recordings are from the frontchannel speaker and which are backchannel signals. We believe this database will make a useful contribution to computer vision, affective computing, and cognitive science communities by providing raw data, features, annotations and baseline comparisons.

Original language	English
Title of host publication	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Pages	277-282
Number of pages	6
DOIs	https://doi.org/10.1109/CVPRW.2013.48
Publication status	Published - 2013 Oct 8
Event	2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013 - Portland, OR, United States Duration: 2013 Jun 23 → 2013 Jun 28

Other

Other	2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013
Country	United States
City	Portland, OR
Period	13/6/23 → 13/6/28

Keywords

Conversations
Database
Facial Expressions

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW.2013.48

Fingerprint Dive into the research topics of 'Cardiff conversation database (CCDB): A database of natural dyadic conversations'. Together they form a unique fingerprint.

Cite this

Aubrey, A. J., Marshall, D., Rosin, P. L., Vendeventer, J., Cunningham, D. W., & Wallraven, C. (2013). Cardiff conversation database (CCDB): A database of natural dyadic conversations. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 277-282). [6595887] https://doi.org/10.1109/CVPRW.2013.48

Cardiff conversation database (CCDB) : A database of natural dyadic conversations. / Aubrey, Andrew J.; Marshall, David; Rosin, Paul L.; Vendeventer, Jason; Cunningham, Douglas W.; Wallraven, Christian.

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2013. p. 277-282 6595887.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Aubrey, AJ, Marshall, D, Rosin, PL, Vendeventer, J, Cunningham, DW & Wallraven, C 2013, Cardiff conversation database (CCDB): A database of natural dyadic conversations. in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops., 6595887, pp. 277-282, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013, Portland, OR, United States, 13/6/23. https://doi.org/10.1109/CVPRW.2013.48

@inproceedings{c0e8530f0b6f498cab98e85ca156f22a,

title = "Cardiff conversation database (CCDB): A database of natural dyadic conversations",

abstract = "We present the Cardiff Conversation Database (CCDb), a unique 2D audiovisual database containing natural conversations between pairs of people. The database currently contains 30 conversations. To date, eight conversations are fully annotated for speaker activity, facial expressions, head motion, and non-verbal utterances. In this paper we describe the data collection and annotation process. We also provide results of baseline experiments in which an SVM classifier was used to identify which parts of the recordings are from the frontchannel speaker and which are backchannel signals. We believe this database will make a useful contribution to computer vision, affective computing, and cognitive science communities by providing raw data, features, annotations and baseline comparisons.",

keywords = "Conversations, Database, Facial Expressions",

author = "Aubrey, {Andrew J.} and David Marshall and Rosin, {Paul L.} and Jason Vendeventer and Cunningham, {Douglas W.} and Christian Wallraven",

year = "2013",

month = oct,

day = "8",

doi = "10.1109/CVPRW.2013.48",

language = "English",

isbn = "9780769549903",

pages = "277--282",

booktitle = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

note = "2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013 ; Conference date: 23-06-2013 Through 28-06-2013",

}

TY - GEN

T1 - Cardiff conversation database (CCDB)

T2 - 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2013

AU - Aubrey, Andrew J.

AU - Marshall, David

AU - Rosin, Paul L.

AU - Vendeventer, Jason

AU - Cunningham, Douglas W.

AU - Wallraven, Christian

PY - 2013/10/8

Y1 - 2013/10/8

N2 - We present the Cardiff Conversation Database (CCDb), a unique 2D audiovisual database containing natural conversations between pairs of people. The database currently contains 30 conversations. To date, eight conversations are fully annotated for speaker activity, facial expressions, head motion, and non-verbal utterances. In this paper we describe the data collection and annotation process. We also provide results of baseline experiments in which an SVM classifier was used to identify which parts of the recordings are from the frontchannel speaker and which are backchannel signals. We believe this database will make a useful contribution to computer vision, affective computing, and cognitive science communities by providing raw data, features, annotations and baseline comparisons.

AB - We present the Cardiff Conversation Database (CCDb), a unique 2D audiovisual database containing natural conversations between pairs of people. The database currently contains 30 conversations. To date, eight conversations are fully annotated for speaker activity, facial expressions, head motion, and non-verbal utterances. In this paper we describe the data collection and annotation process. We also provide results of baseline experiments in which an SVM classifier was used to identify which parts of the recordings are from the frontchannel speaker and which are backchannel signals. We believe this database will make a useful contribution to computer vision, affective computing, and cognitive science communities by providing raw data, features, annotations and baseline comparisons.

KW - Conversations

KW - Database

KW - Facial Expressions

UR - http://www.scopus.com/inward/record.url?scp=84884915067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884915067&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2013.48

DO - 10.1109/CVPRW.2013.48

M3 - Conference contribution

AN - SCOPUS:84884915067

SN - 9780769549903

SP - 277

EP - 282

BT - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Y2 - 23 June 2013 through 28 June 2013

ER -