Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Towards Measuring Continuous Acoustic Feature Convergence in Unconstrained Spoken Dialogues
Kousidis, Spyros; Dorran, David; Wang, Yi; Vaughan, Brian; Cullen, Charlie; Campbell, Dermot; McDonnell, Ciaran; Coyle, Eugene
Acoustic/prosodic feature (a/p) convergence has been known to occur both in dialogues between humans, as well as in human-computer interactions. Understanding the form and function of convergence is desirable for developing next generation conversational agents, as this will help increase speech recognition performance and naturalness of synthesized speech. Currently, the underlying mechanisms by which continuous and bi-directional convergence occurs are not well understood. In this study, a direct comparison between time-aligned frames shows significant similarity in acoustic feature variation between the two speakers. The method described (TAMA) constitutes a first step towards a quantitative analysis of a/p convergence.
Keyword(s): Acoustic-prosodic convergence; dialogue speech; Speech; Life Sciences; Medicine and Health Sciences
Publication Date:
2008
Type: Conference item
Peer-Reviewed: Unknown
Contributor(s): the European Union as part of the SALERO project (www.salero.info) through the IST programme under FP6. Part of the research was also funded by Dublin Institute of Technology
Institution: Dublin Institute of Technology
Citation(s): Conference papers
Publisher(s): Dublin Institute of Technology
File Format(s): application/pdf
First Indexed: 2009-11-23 16:23:56 Last Updated: 2017-12-14 06:40:43