Using prosodic cues to identify dialogue acts: methodological challenge
-
Rein Ove Sikveland
Rein Ove Sikveland is a phonetician with expertise in conversation analysis and call center research. His PhD at the University of York was part of a multidisciplinary European Commission-funded project (“Sound to Sense”) which brought together expertise in speech science and engineering. This paper builds on research done in a Knowledge Transfer Partnership based at the University of Oxford.
und
David Zeitlyn
David Zeitlyn is a social anthropologist who has been doing field research in Cameroon since 1985. He has worked on the sociolinguistics of traditional oratory and used conversation analysis to analyze Mambila spider divination. In collaboration with Bruce Connell, he has worked on several endangered languages on the Nigeria Cameroon border. He has long-standing interests in the application of linguistic theory in different domains (especially IT).
Abstract
This paper addresses the role of prosodic and phonetic features in talk, focussing on how to identify competitive overlaps in conversations. It has previously been claimed that turn competition may be distinguishable from non-competitive overlaps, based on phonetic/prosodic features alone. We test this hypothesis on recordings from a UK-based call center, combining a conversation analytic approach with quantitative methods using a coding scheme. Our long-term aim is to develop large-scale methods operationalizing what we know about conversational sequence and social actions into speech technological applications.
Our findings show that, although there is a tendency for competitive overlaps to be more prominent in terms of loudness and pitch features than non-competitive overlaps, this difference is not sufficient to reliably identify turn competitions from the speech signal itself. We discuss the findings in relation to observations made in individual examples, and conclude by highlighting some of the methodological challenges of applying findings from the linguistic and conversation analytic literature to speech technologies.
About the authors
Rein Ove Sikveland is a phonetician with expertise in conversation analysis and call center research. His PhD at the University of York was part of a multidisciplinary European Commission-funded project (“Sound to Sense”) which brought together expertise in speech science and engineering. This paper builds on research done in a Knowledge Transfer Partnership based at the University of Oxford.
David Zeitlyn is a social anthropologist who has been doing field research in Cameroon since 1985. He has worked on the sociolinguistics of traditional oratory and used conversation analysis to analyze Mambila spider divination. In collaboration with Bruce Connell, he has worked on several endangered languages on the Nigeria Cameroon border. He has long-standing interests in the application of linguistic theory in different domains (especially IT).
Acknowledgments
This research was part of a Knowledge Transfer Partnership, funded by the UK government and by a partner company. Consent was secured via the partner company to conduct this research, and to present the two illustrative examples included in this paper. However, due to confidentiality constraints we cannot disclose the identity of the partner company nor the call center studied. Since the research was, in formal terms, a secondary analysis of anonymized data, informed consent from the speakers was neither possible to obtain nor ethically required.
Appendix. Gesprächsanalytisches Transkriptionssystem 2 (GAT 2) (Selting et al. 2011)
- Sequence structure
- [ ]
- [ ]
Overlaps
- =
“Latching,” a contribution starts immediately where a previous one ends
- Breathing
- .h / h
In-breaths and out-breaths respectively, 0.2–0.5 s.
- .hh / hh
In-breaths and out-breaths respectively, 0.5–0.8 s.
- .hhh / hhh
In-breaths and out-breaths respectively, 0.8–1.0 s.
- .HH / HH
Loud in-/out-breath
- .mh / mh
Nasal in-/out-breath
- .pthh
In-breath initiated by click sound
- Pauses
- (.)
Micro-pause, below 0.2 s.
- (1.0)
Longer pauses indicated by seconds
- Durations
- :
Prolongation of sound/syllable, 0.2–0.5 s.
- Accent
- acCENT
Accented syllable
- Pitch movement at the end of intonation phrases
- ,
Middle rise
- .
Deep fall
- Other conventions
- ˀ
Glottal closure/hold
- ch
Aspirated release
- .tk
Click sound
- huh
Laughter
- l(h)aughter
Aspiration associated with laughing
- (yes)
Candidate hearing
- (he/you)
Possible candidates
References
Baayen, Rolf H. 2008. Analyzing linguistic data: A practical introduction to statistics using R. Cambridge, UK: Cambridge University Press.10.1017/CBO9780511801686Suche in Google Scholar
Barth-Weingarten, Dagmar, Nicole Dehe & Anne Wichmann (eds.). 2009. Where prosody meets pragmatics. Bingley, UK: Emerald.10.1163/9789004253223Suche in Google Scholar
Breiman, Leo, Jerome Friedman, Charles J. Stone & Richard A. Olshen. 1984. Classification and regression trees. Boca Raton, Florida: CRC press.Suche in Google Scholar
Cieslak, David A. & Nitesh V. Chawla. 2008. Learning decision trees for unbalanced data. Paper presented at the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Antwerp, Belgium, 15–19 September.10.1007/978-3-540-87479-9_34Suche in Google Scholar
Couper-Kuhlen, Elizabeth & Margaret Selting. 1996. Prosody in conversation. Cambridge, UK: Cambridge University Press.10.1017/CBO9780511597862Suche in Google Scholar
Deppermann, Arnulf. 2010. Future prospects of research on prosody: The need for publically available corpora: comments on Margaret Selting “Prosody in interaction: State of the art”. In Dagmar Barth-Weingarten, Elizabeth Reber & Margaret Selting (eds.), Prosody in Interaction, 41–50. Amsterdam & Philadelphia: John Benjamins.10.1075/sidag.23.06depSuche in Google Scholar
Edlund, Jens & Mattias Heldner. 2005. Exploring prosody in interaction control. Phonetica 62(2–4). 215–226.10.1159/000090099Suche in Google Scholar
Ford, Cecilia E. & Sandra A. Thompson. 1996. Interactional units in conversation: Syntactic, intonational, and pragmatic resources for the management of turns. Studies in Interactional Sociolinguistics 13. 134–184.10.1017/CBO9780511620874.003Suche in Google Scholar
French, Peter & John Local. 1983. Turn-competetive incomings. Journal of Pragmatics 7. 17–38.10.1016/0378-2166(83)90147-9Suche in Google Scholar
Glenn, Phillip. 2003. Laughter in interaction. Cambridge, UK: Cambridge University Press.10.1017/CBO9780511519888Suche in Google Scholar
Jefferson, Gail. 1984. Notes on some orderlinesses of overlap onset. In Valentina D’Urso & Paol Leonardi (eds.), Discourse analysis and natural rhetoric, 11–38. Padua, Italy: Cleup Editore.Suche in Google Scholar
Kurtic, Emina. 2011. Overlapping talk and turn competition in multi-party conversations. Sheffield: University of Sheffield doctoral dissertation.Suche in Google Scholar
Kurtic, Emina, Guy J. Brown & Bill Wells. 2009. Fundamental frequency height as a resource for the management of overlap in talk-in-interaction. In Dagmar Barth-Weingarten, Nicole Dehe & Anne Wichmann (eds.), Where prosody meets pragmatics, 183–204. Bingley, UK: Emerald Group Publishing Ltd.Suche in Google Scholar
Kurtic, Emina, Guy J. Brown & Bill Wells. 2010. Resources for turn competition in overlap in multi-party conversations: Speech rate, pausing and duration. In Eleventh annual conference of the international speech communication association, 2550–2553.10.21437/Interspeech.2010-690Suche in Google Scholar
Kurtic, Emina, Guy J. Brown & Bill Wells. 2013. Resources for turn competition in overlapping talk. Speech Communication 55. 1–23.10.1016/j.specom.2012.10.002Suche in Google Scholar
Laver, John. 2003. Three semiotic layers of spoken communication. Journal of Phonetics 31(3). 413–415.10.1016/S0095-4470(03)00034-2Suche in Google Scholar
Lerner, Gene H. 1996. On the “semi-permeable” character of grammatical units in conversation: Conditional entry into the turn space of another speaker. In Eleanor Ochs & Emanuel A. Schegloff (eds.), Interaction and grammar, 238–276. Cambridge, UK: Cambridge University Press.10.1017/CBO9780511620874.005Suche in Google Scholar
Local, John. 2004. Getting back to prior talk: And-uh(m) as a back-connecting device in British and American English. In Elizabeth Couper-Kuhlen & Cecilia E. Ford (eds.), Sound patterns in interaction: Cross-linguisitic studies of phonetics and prosody for conversation, 377–400. Amsterdam, The Netherlands: John Benjamins Publishing Company.10.1075/tsl.62.18locSuche in Google Scholar
Local, John. 2005. On the interaction and phonetic design of collaborative completions. In William J. Hardcastle & Janet M. Beck (eds.), A figure of speech: A Festschrift for John Laver, 263–282. New Jersey, NY: Lawrence Erlbaum.Suche in Google Scholar
Oertel, Catharine, Marcin Wlodarczak, Alexey Tarasov, Nick Campbell & Petra Wagner. 2012. Context cues for classification of competitive and collaborative overlaps. Proceedings of Speech Prosody, 721–724. Shanghai, China.Suche in Google Scholar
Robinson, Jeffrey D. 2007. The role of numbers and statistics within conversation analysis. Communication Methods and Measures 1(1). 65–75.10.1080/19312450709336663Suche in Google Scholar
Sacks, Harvey. 1992. In Gail Jefferson with introductions by Emanuel A. Schegloff (eds.), Lectures on conversation, volumes II, Oxford, UK: Blackwell Publishing.Suche in Google Scholar
Schegloff, Emanuel A. 1982. Discourse as an interactional achievement: Some uses of “uh huh” and other things that come between sentences. In D. Tannen (ed.), Analyzing discourse: Text and talk, 71–93. Washington, DC: Georgetown University Press.Suche in Google Scholar
Schegloff, Emanuel A. 2000. Overlapping talk and the organization of turn- taking for conversation. Language in Society 29 (1). 1–63.10.1017/S0047404500001019Suche in Google Scholar
Selting, Margaret. 1996. Prosody as an activity-type distinctive cue in conversation: The case of so-called “astonished” questions in repair initiation. In Elizabeth Couper-Kuhlen & Margaret Selting (eds.), Prosody in conversation, 231–270. Cambridge, UK: Cambridge University Press.10.1017/CBO9780511597862.008Suche in Google Scholar
Selting, Margret, Peter Auer, Dagmar Barth-Weingarten, Jörg R. Bergmann & Pia Bergmann 2011. Gesprächsanalyisches Transkriptionssystem 2 (GAT 2). Gesprächsforschung – Online-Zeitschrift zur verbalen Interaktion, 10. www.gespraechsforschung-ozs.de (accessed 5 December 2010).Suche in Google Scholar
Sidnell, Jack. 2011. Conversation analysis: An introduction, Vol. 45. Hoboken, New Jersey: John Wiley & Sons.Suche in Google Scholar
Steensig, Jakob & Trine Heinemann. 2015. Opening up codings?. Research on Language and Social Interaction 48(1). 20–25.10.1080/08351813.2015.993838Suche in Google Scholar
Stivers, Tanya, Nicholas J. Enfield, Penelope Brown, Christina Englert & Makoto Hayashi. 2009. Universals and cultural variation in turn-taking in conversation. Proceedings of the National Academy of Sciences 106(26). 10587–10592.10.1073/pnas.0903616106Suche in Google Scholar
Stivers, Tanya & Nick J. Enfield. 2010. A coding scheme for question–response sequences in conversation. Journal of Pragmatics 42(10). 2620–2626.10.1016/j.pragma.2010.04.002Suche in Google Scholar
Szczepek Reed, Beatrice. 2009. Prosodic orientation: A practice for sequence organization in broadcast telephone openings. Journal of Pragmatics 41(6). 1223–1247.10.1016/j.pragma.2008.08.009Suche in Google Scholar
Szczepek Reed, Beatrice. 2010. Prosody and alignment: A sequential perspective. Cultural Studies of Science Education 5(4). 859–867.10.1007/s11422-010-9289-zSuche in Google Scholar
Szczepek Reed, Beatrice. 2011. Beyond the particular: Prosody and the coordination of actions. Language and Speech 55(1). 13–34.10.1177/0023830911428871Suche in Google Scholar
Szczepek Reed, Beatrice. 2015. Managing the Boundary Between “Yes” and “But”: Two Ways of Disaffiliating With German ja aber and jaber. Research on Language and Social Interaction 48(1). 32–57.10.1080/08351813.2015.993843Suche in Google Scholar
Tracy, Karen. 2007. The role (or not) for numbers and statistics in qualitative research: An introduction. Communication Methods and Measures 1(1). 31–35.10.1080/19312450709336659Suche in Google Scholar
Walker, Gareth. 2004. On some interactional and phonetic properties of increments to turns in talk-in-interaction. In Elizabeth Couper-Kuhlen & Cecilia Ford (eds.), Sound patterns in interaction, 147–169. Amsterdam, The Netherlands: John Benjamins.10.1075/tsl.62.10walSuche in Google Scholar
Wells, Bill & Sarah Macfarlane. 1998. Prosody as an interactional resource: Turn- projection and overlap. Language and Speech 41(3–4). 265–294.10.1177/002383099804100403Suche in Google Scholar
Wichmann, Anne. 2011. Prosody and pragmatic effects. In Gisle Andersen & Karin Aijmer (eds.), Pragmatics of society, Vol. 5, 181–212. Göttingen, Germany: De Gruyter.10.1515/9783110214420.181Suche in Google Scholar
Zeitlyn, David. forthcoming. Talking Kinship: Doing kinship – some Mambila cases. (Kinship? Anthropology? Emergency! Emergency! Notes for a 21st Century Anthropology.). In Jon Abbink (ed.), Rhetoric in social relations. Oxford: Berghan Books.Suche in Google Scholar
Zuraidah, Mohd Don & Gerry Knowles. 2006. Prosody and turn-taking in Malay broadcast interviews. Journal of Pragmatics 38(4). 490–512.10.1016/j.pragma.2005.11.003Suche in Google Scholar
© 2017 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Articles
- The discourse connector list: a multi-genre cross-cultural corpus analysis
- Using prosodic cues to identify dialogue acts: methodological challenge
- Embodiment in Moroccan Arabic storytelling: language, stance and discourse analysis
- Father identities constructed through meaning choices: a systemic-functional analysis of fathers’ letters in Dad Where Are We Going
- “I don’t think” versus “I think + not”
Artikel in diesem Heft
- Frontmatter
- Articles
- The discourse connector list: a multi-genre cross-cultural corpus analysis
- Using prosodic cues to identify dialogue acts: methodological challenge
- Embodiment in Moroccan Arabic storytelling: language, stance and discourse analysis
- Father identities constructed through meaning choices: a systemic-functional analysis of fathers’ letters in Dad Where Are We Going
- “I don’t think” versus “I think + not”
