1 Citation (Scopus)

Abstract

Acoustic-prosodic entrainment describes the tendency of humans to align or adapt their speech acoustics to each other in conversation. This alignment of spoken behavior has important implications for conversational success. However, modeling the subtle nature of entrainment in spoken dialogue continues to pose a challenge. In this paper, we propose a straightforward definition for local entrainment in the speech domain and opera-tionalize an algorithm based on this: acoustic-prosodic features that capture entrainment should be maximally different between real conversations involving two partners and sham conversations generated by randomly mixing the speaking turns from the original two conversational partners. We propose an approach for measuring local entrainment that quantifies alignment of behavior on a turn-by-turn basis, projecting the differences between interlocutors' acoustic-prosodic features for a given turn onto a discriminative feature subspace that maximizes the difference between real and sham conversations. We evaluate the method using the derived features to drive a classifier aiming to predict an objective measure of conversational success (i.e., low versus high), on a corpus of task-oriented conversations. The proposed entrainment approach achieves 72% classification accuracy using a Naive Bayes classifier, outperforming three previously established approaches evaluated on the same conversational corpus.

Original languageEnglish (US)
Pages (from-to)581-585
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2018-September
DOIs
StatePublished - Jan 1 2018
Event19th Annual Conference of the International Speech Communication, INTERSPEECH 2018 - Hyderabad, India
Duration: Sep 2 2018Sep 6 2018

Fingerprint

Entrainment
Acoustics
Classifiers
Alignment
Naive Bayes Classifier
Quantify
Continue
Maximise
Classifier
Subspace
Predict
Evaluate
Modeling

Keywords

  • Conversational Success
  • Entrainment
  • Linear Discriminant Analysis
  • Spoken Dialogue Systems

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation

Cite this

A discriminative acoustic-prosodic approach for measuring local entrainment. / Willi, Megan M.; Borrie, Stephanie A.; Barrett, Tyson S.; Tu, Ming; Berisha, Visar.

In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2018-September, 01.01.2018, p. 581-585.

Research output: Contribution to journalConference article

@article{ff0bca4d842843d19d77098ed74709b6,
title = "A discriminative acoustic-prosodic approach for measuring local entrainment",
abstract = "Acoustic-prosodic entrainment describes the tendency of humans to align or adapt their speech acoustics to each other in conversation. This alignment of spoken behavior has important implications for conversational success. However, modeling the subtle nature of entrainment in spoken dialogue continues to pose a challenge. In this paper, we propose a straightforward definition for local entrainment in the speech domain and opera-tionalize an algorithm based on this: acoustic-prosodic features that capture entrainment should be maximally different between real conversations involving two partners and sham conversations generated by randomly mixing the speaking turns from the original two conversational partners. We propose an approach for measuring local entrainment that quantifies alignment of behavior on a turn-by-turn basis, projecting the differences between interlocutors' acoustic-prosodic features for a given turn onto a discriminative feature subspace that maximizes the difference between real and sham conversations. We evaluate the method using the derived features to drive a classifier aiming to predict an objective measure of conversational success (i.e., low versus high), on a corpus of task-oriented conversations. The proposed entrainment approach achieves 72{\%} classification accuracy using a Naive Bayes classifier, outperforming three previously established approaches evaluated on the same conversational corpus.",
keywords = "Conversational Success, Entrainment, Linear Discriminant Analysis, Spoken Dialogue Systems",
author = "Willi, {Megan M.} and Borrie, {Stephanie A.} and Barrett, {Tyson S.} and Ming Tu and Visar Berisha",
year = "2018",
month = "1",
day = "1",
doi = "10.21437/Interspeech.2018-1419",
language = "English (US)",
volume = "2018-September",
pages = "581--585",
journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
issn = "2308-457X",

}

TY - JOUR

T1 - A discriminative acoustic-prosodic approach for measuring local entrainment

AU - Willi, Megan M.

AU - Borrie, Stephanie A.

AU - Barrett, Tyson S.

AU - Tu, Ming

AU - Berisha, Visar

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Acoustic-prosodic entrainment describes the tendency of humans to align or adapt their speech acoustics to each other in conversation. This alignment of spoken behavior has important implications for conversational success. However, modeling the subtle nature of entrainment in spoken dialogue continues to pose a challenge. In this paper, we propose a straightforward definition for local entrainment in the speech domain and opera-tionalize an algorithm based on this: acoustic-prosodic features that capture entrainment should be maximally different between real conversations involving two partners and sham conversations generated by randomly mixing the speaking turns from the original two conversational partners. We propose an approach for measuring local entrainment that quantifies alignment of behavior on a turn-by-turn basis, projecting the differences between interlocutors' acoustic-prosodic features for a given turn onto a discriminative feature subspace that maximizes the difference between real and sham conversations. We evaluate the method using the derived features to drive a classifier aiming to predict an objective measure of conversational success (i.e., low versus high), on a corpus of task-oriented conversations. The proposed entrainment approach achieves 72% classification accuracy using a Naive Bayes classifier, outperforming three previously established approaches evaluated on the same conversational corpus.

AB - Acoustic-prosodic entrainment describes the tendency of humans to align or adapt their speech acoustics to each other in conversation. This alignment of spoken behavior has important implications for conversational success. However, modeling the subtle nature of entrainment in spoken dialogue continues to pose a challenge. In this paper, we propose a straightforward definition for local entrainment in the speech domain and opera-tionalize an algorithm based on this: acoustic-prosodic features that capture entrainment should be maximally different between real conversations involving two partners and sham conversations generated by randomly mixing the speaking turns from the original two conversational partners. We propose an approach for measuring local entrainment that quantifies alignment of behavior on a turn-by-turn basis, projecting the differences between interlocutors' acoustic-prosodic features for a given turn onto a discriminative feature subspace that maximizes the difference between real and sham conversations. We evaluate the method using the derived features to drive a classifier aiming to predict an objective measure of conversational success (i.e., low versus high), on a corpus of task-oriented conversations. The proposed entrainment approach achieves 72% classification accuracy using a Naive Bayes classifier, outperforming three previously established approaches evaluated on the same conversational corpus.

KW - Conversational Success

KW - Entrainment

KW - Linear Discriminant Analysis

KW - Spoken Dialogue Systems

UR - http://www.scopus.com/inward/record.url?scp=85054993468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054993468&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2018-1419

DO - 10.21437/Interspeech.2018-1419

M3 - Conference article

VL - 2018-September

SP - 581

EP - 585

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

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

SN - 2308-457X

ER -