Evaluation of call centre conversations based on a high-level symbolic representation

Leticia Arco; Carlos Alberto Martínez Mosquera; Fabjola Braho; Yisel Clavel; Johan Loeckx

doi:10.21437/Interspeech.2022

Evaluation of call centre conversations based on a high-level symbolic representation

Leticia Arco, Carlos Alberto Martínez Mosquera, Fabjola Braho, Yisel Clavel , Johan Loeckx

Informatics and Applied Informatics

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

79 Downloads (Pure)

Abstract

We present a demo that illustrates the performance of our system to analyse and evaluate call centre conversations. Our solution can be used at different stages of the quality feedback loop. The high-level symbolic representation developed on the context-based intent recognition core module allows for detecting fine-grained reasons for quality assurance problems and going in-depth qualitative analysis of how agents and customers interact. We illustrate the evaluation and insights of real-life conversations provided by a Belgian call centre. Participants can interact with the demo by playing with call annotation, recommendations, and diverse parameters.

Original language	English
Title of host publication	Proceedings of the INTERSPEECH 2022 Conference
Editors	Hanseok Ko, John H. L. Hansen
Place of Publication	Incheon, Korea
Publisher	ISCA
Chapter	Show and Tell III
Pages	3663-3664
Number of pages	2
Volume	2022-September
DOIs	https://doi.org/10.21437/Interspeech.2022
Publication status	Published - 18 Sep 2022
Event	23rd INTERSPEECH Conference: Human and Humanizing Speech Technology - Songdo ConvensiA, Incheon, Korea, Republic of Duration: 18 Sep 2022 → 22 Sep 2022 Conference number: 23 https://www.interspeech2022.org/general/

Publication series

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

Conference

Conference	23rd INTERSPEECH Conference
Abbreviated title	INTERSPEECH
Country/Territory	Korea, Republic of
City	Incheon
Period	18/09/22 → 22/09/22
Internet address	https://www.interspeech2022.org/general/

Bibliographical note

Funding Information:
This research was carried out as part of the SYNAPS project in collaboration with Nixxis, ETRO, and a Belgian call centre, funded by Innoviris. The authors gratefully acknowledge the VUB AI applied research team members, Izmir Khalish, and Benjamin Jan Vermunicht for their contribution.

Publisher Copyright:
Copyright © 2022 ISCA.

Copyright:
Copyright 2022 Elsevier B.V., All rights reserved.

Keywords

Call monitoring
Intent recognition
Human-human interaction
Recommender system

Access to Document

10.21437/Interspeech.2022

arco22_interspeechFinal published version, 402 KB

https://www.isca-speech.org/archive/pdfs/interspeech_2022/arco22_interspeech.pdf

Cite this

Arco, L., Martínez Mosquera, C. A., Braho, F., Clavel , Y., & Loeckx, J. (2022). Evaluation of call centre conversations based on a high-level symbolic representation. In H. Ko, & J. H. L. Hansen (Eds.), Proceedings of the INTERSPEECH 2022 Conference (Vol. 2022-September, pp. 3663-3664). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). ISCA. https://doi.org/10.21437/Interspeech.2022

Arco, Leticia ; Martínez Mosquera, Carlos Alberto ; Braho, Fabjola ; Clavel , Yisel ; Loeckx, Johan. / Evaluation of call centre conversations based on a high-level symbolic representation. Proceedings of the INTERSPEECH 2022 Conference. editor / Hanseok Ko ; John H. L. Hansen. Vol. 2022-September Incheon, Korea : ISCA, 2022. pp. 3663-3664 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{31decc6bbb0245ae979a19025a35b50b,

title = "Evaluation of call centre conversations based on a high-level symbolic representation",

abstract = "We present a demo that illustrates the performance of our system to analyse and evaluate call centre conversations. Our solution can be used at different stages of the quality feedback loop. The high-level symbolic representation developed on the context-based intent recognition core module allows for detecting fine-grained reasons for quality assurance problems and going in-depth qualitative analysis of how agents and customers interact. We illustrate the evaluation and insights of real-life conversations provided by a Belgian call centre. Participants can interact with the demo by playing with call annotation, recommendations, and diverse parameters.",

keywords = "Call monitoring, Intent recognition, Human-human interaction, Recommender system",

author = "Leticia Arco and {Mart{\'i}nez Mosquera}, {Carlos Alberto} and Fabjola Braho and Yisel Clavel and Johan Loeckx",

note = "Funding Information: This research was carried out as part of the SYNAPS project in collaboration with Nixxis, ETRO, and a Belgian call centre, funded by Innoviris. The authors gratefully acknowledge the VUB AI applied research team members, Izmir Khalish, and Benjamin Jan Vermunicht for their contribution. Publisher Copyright: Copyright {\textcopyright} 2022 ISCA. Copyright: Copyright 2022 Elsevier B.V., All rights reserved.; 23rd INTERSPEECH Conference : Human and Humanizing Speech Technology, INTERSPEECH ; Conference date: 18-09-2022 Through 22-09-2022",

year = "2022",

month = sep,

day = "18",

doi = "10.21437/Interspeech.2022",

language = "English",

volume = "2022-September",

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

publisher = "ISCA",

pages = "3663--3664",

editor = "Hanseok Ko and Hansen, {John H. L.}",

booktitle = "Proceedings of the INTERSPEECH 2022 Conference",

url = "https://www.interspeech2022.org/general/",

}

Arco, L, Martínez Mosquera, CA, Braho, F, Clavel , Y & Loeckx, J 2022, Evaluation of call centre conversations based on a high-level symbolic representation. in H Ko & JHL Hansen (eds), Proceedings of the INTERSPEECH 2022 Conference. vol. 2022-September, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISCA, Incheon, Korea, pp. 3663-3664, 23rd INTERSPEECH Conference, Incheon, Korea, Republic of, 18/09/22. https://doi.org/10.21437/Interspeech.2022

Evaluation of call centre conversations based on a high-level symbolic representation. / Arco, Leticia; Martínez Mosquera, Carlos Alberto; Braho, Fabjola; Clavel , Yisel; Loeckx, Johan.

Proceedings of the INTERSPEECH 2022 Conference. ed. / Hanseok Ko; John H. L. Hansen. Vol. 2022-September Incheon, Korea : ISCA, 2022. p. 3663-3664 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

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

TY - GEN

T1 - Evaluation of call centre conversations based on a high-level symbolic representation

AU - Arco, Leticia

AU - Martínez Mosquera, Carlos Alberto

AU - Braho, Fabjola

AU - Clavel , Yisel

AU - Loeckx, Johan

N1 - Conference code: 23

PY - 2022/9/18

Y1 - 2022/9/18

N2 - We present a demo that illustrates the performance of our system to analyse and evaluate call centre conversations. Our solution can be used at different stages of the quality feedback loop. The high-level symbolic representation developed on the context-based intent recognition core module allows for detecting fine-grained reasons for quality assurance problems and going in-depth qualitative analysis of how agents and customers interact. We illustrate the evaluation and insights of real-life conversations provided by a Belgian call centre. Participants can interact with the demo by playing with call annotation, recommendations, and diverse parameters.

AB - We present a demo that illustrates the performance of our system to analyse and evaluate call centre conversations. Our solution can be used at different stages of the quality feedback loop. The high-level symbolic representation developed on the context-based intent recognition core module allows for detecting fine-grained reasons for quality assurance problems and going in-depth qualitative analysis of how agents and customers interact. We illustrate the evaluation and insights of real-life conversations provided by a Belgian call centre. Participants can interact with the demo by playing with call annotation, recommendations, and diverse parameters.

KW - Call monitoring

KW - Intent recognition

KW - Human-human interaction

KW - Recommender system

UR - https://www.isca-speech.org/archive/interspeech_2022/index.html

UR - http://www.scopus.com/inward/record.url?scp=85140077234&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2022

DO - 10.21437/Interspeech.2022

M3 - Conference paper

VL - 2022-September

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

SP - 3663

EP - 3664

BT - Proceedings of the INTERSPEECH 2022 Conference

A2 - Ko, Hanseok

A2 - Hansen, John H. L.

PB - ISCA

CY - Incheon, Korea

T2 - 23rd INTERSPEECH Conference

Y2 - 18 September 2022 through 22 September 2022

ER -

Arco L, Martínez Mosquera CA, Braho F, Clavel Y, Loeckx J. Evaluation of call centre conversations based on a high-level symbolic representation. In Ko H, Hansen JHL, editors, Proceedings of the INTERSPEECH 2022 Conference. Vol. 2022-September. Incheon, Korea: ISCA. 2022. p. 3663-3664. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). https://doi.org/10.21437/Interspeech.2022

Evaluation of call centre conversations based on a high-level symbolic representation

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this