Speech Rate Adjustments in Conversations With an Amazon Alexa Socialbot
This paper investigates users’ speech rate adjustments during conversations with an Amazon Alexa socialbot in response to situational (in-lab vs. at-home) and communicative (ASR comprehension errors) factors. We collected user interaction studies and measured speech rate at each turn in the conversa...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-05-01
|
Series: | Frontiers in Communication |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fcomm.2021.671429/full |
id |
doaj-71a6555fc79f4d0da0e17d3638ffce61 |
---|---|
record_format |
Article |
spelling |
doaj-71a6555fc79f4d0da0e17d3638ffce612021-05-07T08:13:51ZengFrontiers Media S.A.Frontiers in Communication2297-900X2021-05-01610.3389/fcomm.2021.671429671429Speech Rate Adjustments in Conversations With an Amazon Alexa SocialbotMichelle Cohn0Michelle Cohn1Kai-Hui Liang2Kai-Hui Liang3Melina Sarian4Georgia Zellou5Zhou Yu6Zhou Yu7Phonetics Lab, University of California, Davis, CA, United StatesNatural Language Processing Lab, University of California, Davis, CA, United StatesNatural Language Processing Lab, University of California, Davis, CA, United StatesDepartment of Computer Science, Columbia University, New York, NY, United StatesPhonetics Lab, University of California, Davis, CA, United StatesPhonetics Lab, University of California, Davis, CA, United StatesNatural Language Processing Lab, University of California, Davis, CA, United StatesDepartment of Computer Science, Columbia University, New York, NY, United StatesThis paper investigates users’ speech rate adjustments during conversations with an Amazon Alexa socialbot in response to situational (in-lab vs. at-home) and communicative (ASR comprehension errors) factors. We collected user interaction studies and measured speech rate at each turn in the conversation and in baseline productions (collected prior to the interaction). Overall, we find that users slow their speech rate when talking to the bot, relative to their pre-interaction productions, consistent with hyperarticulation. Speakers use an even slower speech rate in the in-lab setting (relative to at-home). We also see evidence for turn-level entrainment: the user follows the directionality of Alexa’s changes in rate in the immediately preceding turn. Yet, we do not see differences in hyperarticulation or entrainment in response to ASR errors, or on the basis of user ratings of the interaction. Overall, this work has implications for human-computer interaction and theories of linguistic adaptation and entrainment.https://www.frontiersin.org/articles/10.3389/fcomm.2021.671429/fullvocal entrainmentsocialbotvoice-activated artificially intelligent assistantnon-task oriented conversationshuman-computer interactionhyperarticulation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Michelle Cohn Michelle Cohn Kai-Hui Liang Kai-Hui Liang Melina Sarian Georgia Zellou Zhou Yu Zhou Yu |
spellingShingle |
Michelle Cohn Michelle Cohn Kai-Hui Liang Kai-Hui Liang Melina Sarian Georgia Zellou Zhou Yu Zhou Yu Speech Rate Adjustments in Conversations With an Amazon Alexa Socialbot Frontiers in Communication vocal entrainment socialbot voice-activated artificially intelligent assistant non-task oriented conversations human-computer interaction hyperarticulation |
author_facet |
Michelle Cohn Michelle Cohn Kai-Hui Liang Kai-Hui Liang Melina Sarian Georgia Zellou Zhou Yu Zhou Yu |
author_sort |
Michelle Cohn |
title |
Speech Rate Adjustments in Conversations With an Amazon Alexa Socialbot |
title_short |
Speech Rate Adjustments in Conversations With an Amazon Alexa Socialbot |
title_full |
Speech Rate Adjustments in Conversations With an Amazon Alexa Socialbot |
title_fullStr |
Speech Rate Adjustments in Conversations With an Amazon Alexa Socialbot |
title_full_unstemmed |
Speech Rate Adjustments in Conversations With an Amazon Alexa Socialbot |
title_sort |
speech rate adjustments in conversations with an amazon alexa socialbot |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Communication |
issn |
2297-900X |
publishDate |
2021-05-01 |
description |
This paper investigates users’ speech rate adjustments during conversations with an Amazon Alexa socialbot in response to situational (in-lab vs. at-home) and communicative (ASR comprehension errors) factors. We collected user interaction studies and measured speech rate at each turn in the conversation and in baseline productions (collected prior to the interaction). Overall, we find that users slow their speech rate when talking to the bot, relative to their pre-interaction productions, consistent with hyperarticulation. Speakers use an even slower speech rate in the in-lab setting (relative to at-home). We also see evidence for turn-level entrainment: the user follows the directionality of Alexa’s changes in rate in the immediately preceding turn. Yet, we do not see differences in hyperarticulation or entrainment in response to ASR errors, or on the basis of user ratings of the interaction. Overall, this work has implications for human-computer interaction and theories of linguistic adaptation and entrainment. |
topic |
vocal entrainment socialbot voice-activated artificially intelligent assistant non-task oriented conversations human-computer interaction hyperarticulation |
url |
https://www.frontiersin.org/articles/10.3389/fcomm.2021.671429/full |
work_keys_str_mv |
AT michellecohn speechrateadjustmentsinconversationswithanamazonalexasocialbot AT michellecohn speechrateadjustmentsinconversationswithanamazonalexasocialbot AT kaihuiliang speechrateadjustmentsinconversationswithanamazonalexasocialbot AT kaihuiliang speechrateadjustmentsinconversationswithanamazonalexasocialbot AT melinasarian speechrateadjustmentsinconversationswithanamazonalexasocialbot AT georgiazellou speechrateadjustmentsinconversationswithanamazonalexasocialbot AT zhouyu speechrateadjustmentsinconversationswithanamazonalexasocialbot AT zhouyu speechrateadjustmentsinconversationswithanamazonalexasocialbot |
_version_ |
1721455827685998592 |