Zobrazit v EDS

NaturalTurn: a method to segment speech into psychologically meaningful conversational turns.

Uloženo v:
Podrobná bibliografie
Název: NaturalTurn: a method to segment speech into psychologically meaningful conversational turns.
Autoři: Cooney G; The Wharton School, University of Pennsylvania, Philadelphia, PA, USA. guscooney@gmail.com.; Department of Psychological and Brain Sciences, Dartmouth College, Hanover, NH, USA. guscooney@gmail.com., Reece A; BetterUp Inc, Austin, TX, USA.
Zdroj: Scientific reports [Sci Rep] 2025 Nov 07; Vol. 15 (1), pp. 39155. Date of Electronic Publication: 2025 Nov 07.
Způsob vydávání: Journal Article
Jazyk: English
Informace o časopise: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Imprint Name(s): Original Publication: London : Nature Publishing Group, copyright 2011-
Výrazy ze slovníku MeSH: Speech* , Communication* , Social Interaction*, Humans ; Algorithms ; Interpersonal Relations
Abstrakt: Competing Interests: Declarations. Competing interests: At the time this project was conducted, AR was an employee, and GC was a consultant at BetterUp Inc. The authors declare that they have no other competing interests.
Conversation is a subject of increasing interest in the social, cognitive, and computational sciences. Yet as conversational datasets continue to increase in size and complexity, researchers lack scalable methods to segment speech-to-text transcripts into conversational "turns"-the basic building blocks of social interaction. We discuss this challenge and then introduce "NaturalTurn," a turn-segmentation algorithm designed to accurately capture the dynamics of conversational exchange. NaturalTurn operates by distinguishing speakers' primary conversational turns from listeners' secondary utterances, such as backchannels, brief interjections, and other forms of parallel speech that characterize human conversation. Using data from a large conversation corpus, we show that NaturalTurn captures conversational turns more accurately than a baseline model. For example, it produces turns with durations and gaps that match empirical literature, reveals stronger linguistic alignment patterns between speakers, and uncovers otherwise hidden relationships between turn-taking and affective outcomes. NaturalTurn thus represents a pragmatic development in machine-generated transcript-processing methods, or "turn models", that will enable researchers to link turn-taking dynamics with important outcomes of social interaction, a central goal of conversation science.
(© 2025. The Author(s).)
Komentáře: Erratum in: Sci Rep. 2025 Dec 1;15(1):42892. doi: 10.1038/s41598-025-30188-x.. (PMID: 41326579)
References: J Phon. 2021 Sep;88:. (PMID: 34366499)
Proc Natl Acad Sci U S A. 1940 Jan 15;26(1):10-6. (PMID: 16577954)
Front Psychol. 2015 Mar 03;6:236. (PMID: 25784894)
Cognition. 2022 Jun;223:105037. (PMID: 35123218)
Trends Cogn Sci. 2016 Jan;20(1):6-14. (PMID: 26651245)
J Commun Disord. 2013 May-Jun;46(3):294-308. (PMID: 23562700)
Proc Natl Acad Sci U S A. 2009 Jun 30;106(26):10587-92. (PMID: 19553212)
Proc Natl Acad Sci U S A. 1939 Feb;25(2):58-67. (PMID: 16588269)
Front Psychol. 2015 Sep 29;6:1492. (PMID: 26483741)
Psychol Bull. 1981 Jan;89(1):101-32. (PMID: 7232607)
Trends Cogn Sci. 2019 Feb;23(2):158-169. (PMID: 30522867)
J Exp Psychol Hum Percept Perform. 2016 Sep;42(9):1297-310. (PMID: 26962844)
Am Psychol. 2017 Sep;72(6):517-530. (PMID: 28880099)
Proc Natl Acad Sci U S A. 2022 Jan 25;119(4):. (PMID: 35042815)
Cogn Sci. 2020 Nov;44(11):e12911. (PMID: 33124090)
Sci Adv. 2023 Mar 31;9(13):eadf3197. (PMID: 37000886)
Phonetica. 2005 Apr-Dec;62(2-4):215-26. (PMID: 16391504)
J Phon. 2022 Sep;94:. (PMID: 37599902)
Psychol Sci. 2012 Aug 1;23(8):931-9. (PMID: 22810169)
Int J Lang Commun Disord. 2014 Jan-Feb;49(1):15-29. (PMID: 24372883)
Annu Rev Psychol. 2023 Jan 18;74:299-332. (PMID: 36130067)
Psychol Sci. 2011 Jan;22(1):39-44. (PMID: 21149854)
Front Psychol. 2015 Jun 12;6:731. (PMID: 26124727)
Curr Opin Psychol. 2020 Feb;31:22-27. (PMID: 31404835)
Contributed Indexing: Keywords: Alignment; Backchannels; Convergence; Conversation; Natural language processing; Social interaction; Speech-to-text transcript; Synchrony; Turn segmentation; Turn-taking
Entry Date(s): Date Created: 20251107 Date Completed: 20251107 Latest Revision: 20251203
Update Code: 20251203
PubMed Central ID: PMC12595032
DOI: 10.1038/s41598-025-24381-1
PMID: 41203693
Databáze: MEDLINE
Popis
Abstrakt:Competing Interests: Declarations. Competing interests: At the time this project was conducted, AR was an employee, and GC was a consultant at BetterUp Inc. The authors declare that they have no other competing interests.<br />Conversation is a subject of increasing interest in the social, cognitive, and computational sciences. Yet as conversational datasets continue to increase in size and complexity, researchers lack scalable methods to segment speech-to-text transcripts into conversational "turns"-the basic building blocks of social interaction. We discuss this challenge and then introduce "NaturalTurn," a turn-segmentation algorithm designed to accurately capture the dynamics of conversational exchange. NaturalTurn operates by distinguishing speakers' primary conversational turns from listeners' secondary utterances, such as backchannels, brief interjections, and other forms of parallel speech that characterize human conversation. Using data from a large conversation corpus, we show that NaturalTurn captures conversational turns more accurately than a baseline model. For example, it produces turns with durations and gaps that match empirical literature, reveals stronger linguistic alignment patterns between speakers, and uncovers otherwise hidden relationships between turn-taking and affective outcomes. NaturalTurn thus represents a pragmatic development in machine-generated transcript-processing methods, or "turn models", that will enable researchers to link turn-taking dynamics with important outcomes of social interaction, a central goal of conversation science.<br /> (© 2025. The Author(s).)
ISSN:2045-2322
DOI:10.1038/s41598-025-24381-1