Exploring Prosody in Interaction Control

This paper investigates prosodic aspects of turn-taking in conversation with aview to improving the efficiency of identifying relevant places at which a machinecan legitimately begin to talk to a human interlocutor. It examines the relationshipbetween interaction control, the communicative function of which is to regulatethe flow of information between interlocutors, and its phonetic manifestation.Specifically, the listener’s perception of such interaction control phenomena ismodelled. Algorithms for automatic online extraction of prosodic phenomenaliable to be relevant for interaction control, such as silent pauses and intonationpatterns, are presented and evaluated in experiments using Swedish map taskdata. We show that the automatically extracted prosodic features can be used toavoid many of the places where current dialogue systems run the risk of interrupt-ingtheir users, as well as to identify suitable places to take the turn.

[1]  S. MacFarlane,et al.  Prosody as an Interactional Resource: Turn-projection and Overlap , 1998, Language and speech.

[2]  John Local,et al.  Projection and ‘silences’: Notes on phonetic and conversational structure , 1986 .

[3]  Joakim Nivre,et al.  On the Semantics and Pragmatics of Linguistic Feedback , 1992, J. Semant..

[4]  Anne H. Anderson,et al.  The Hcrc Map Task Corpus , 1991 .

[5]  Johan Boye,et al.  Real-time Handling of Fragmented Utterances , 2001 .

[6]  S. Duncan,et al.  Some Signals and Rules for Taking Speaking Turns in Conversations , 1972 .

[7]  Mattias Heldner,et al.  Utterance segmentation and turn-taking in spoken dialogue systems , 2005 .

[8]  P. Mermelstein.  Automatic segmentation of speech into syllabic units. , 1975, The Journal of the Acoustical Society of America.

[9]  Richard Ogden.  Turn transition, creak and glottal stop in Finnish talk-in-interaction , 2001, Journal of the International Phonetic Association.

[10]  R. Carlson,et al.  INTERRUPTION IMPOSSIBLE , 2004 .

[11]  Jens Edlund,et al.  Robust interpretation in the Higgins spoken dialogue system , 2004 .

[12]  John Local,et al.  Phonology for conversation: Phonetic aspects of turn delimitation in London Jamaican , 1985 .

[13]  Cecilia E. Ford,et al.  Interactional units in conversation: Syntactic, intonational, and pragmatic resources for the mana , 1996 .

[14]  Johanneke Caspers,et al.  Local speech melody as a limiting factor in the turn-taking system in Dutch , 2003, J. Phonetics.

[15]  M. Selting.  On the Interplay of Syntax and Prosody in the Constitution of Turn-Constructional Units and Turns in Conversation , 1996 .

[16]  Yasuharu Den,et al.  Prosody-based detection of the context of backchannel responses , 1998, ICSLP.

[17]  Cecilia E. Ford,et al.  Interaction and grammar: Interactional units in conversation: syntactic, intonational, and pragmatic resources for the management of turns , 1996 .

[18]  Pétur Helgason,et al.  Preaspiration in the Nordic languages : synchronic and diachronic aspects , 2002 .

[19]  Nigel G. Ward,et al.  Prosodic features which cue back-channel responses in English and Japanese , 2000 .

[20]  A. Ichikawa,et al.  An Analysis of Turn-Taking and Backchannels Based on Prosodic and Syntactic Features in Japanese Map Task Dialogs , 1998, Language and speech.

[21]  J. Local,et al.  Towards a phonology of conversation: turn-taking in Tyneside English , 1986, Journal of Linguistics.