The Prosody of Turn-Taking and Dialog Acts

A Special Session at Interspeech 2006

A recent focus of research interest is the use of prosody for improved utterance-type tagging and for the swift and accurate detection of dialog events such as turn ends, back-channel invitations, disfluencies, and clause and sentence boundaries. Applications include better language modeling, improved pragmatic accuracy in dialog systems, improved timing in dialog systems, and potential insights into the cognitive mechanisms and social dynamics of human interaction.

This workshop will provide a venue not only for research contributions but also for in-depth discussions of underlying issues. The aim is to bring together researchers working from different perspectives to share techniques and attain a clearer understanding of how prosodic markers to dialog acts fit into the larger ecology of prosodic phenomena and the larger picture of spoken language applications.

Main-Session Papers (Wednesday, September 20, 16:30 - 18:30)

Skantz et al.: User Responses to Prosodic Variation in Fragmentary Grounding Utterances in Dialog ; (slides)

Ishi et al.: Analysis of prosodic and linguistic cues of phrase finals for turn-taking and dialog acts ; (slides)

Schlangen: From Reaction To Prediction: Experiments with Computational Models of Turn-Taking ; (slides)

Kolar et al.: On Speaker-Specific Prosodic Models for Automatic Dialog Act Segmentation of Multi-Party Meetings ; (slides)

Ward & Al Bayyari: A Case Study in the Identification of Prosodic Cues to Turn-Taking: Back-Channeling in Arabic; (slides)

Edlund & Heldner: /nailon/ -- Software for Online Analysis of Prosody; (slides)

Poster Session Papers

Barkhuysen et al.: How Auditory and Visual Prosody is Used in End-of-Utterance Detection

Solorio et al.: Prosodic Feature Generation for Back-channel Prediction

Tepperman et al.: "Yeah Right": Sarcasm Recognition for Spoken Dialogue Systems

Wesseling et al.: On the Sufficiency and Redundancy of Pitch for TRP Projection


Topics of Interest include:


Papers were reviewed by the normal Interspeech process.

Organizing Committee

Nigel Ward, University of Texas at El Paso (
Johanneke Caspers, University of Leiden
Shinya Fujie, Waseda University
Elizabeth Shriberg, SRI and ICSI
Marc Swerts, Tilberg University


ETR Workshop on Dialogue and Prosody, Veldhoven, 1999

USC-UTEP Workshop on Predictive Models of Human Communication Dynamics, 2010

Workshop on Modeling Human Communication Dynamics at NIPS 2010.

Feedback Behaviors in Dialog at Interspeech 2012.

Prosodic Constructions in Dialog at IPrA 2014.

March 28, 2006  Nigel Ward