Utilising Hidden Markov Modelling for the Assessment of Accommodation in Conversational Speech

Solanki, V., Vinciarelli, A. , Stuart-Smith, J. and Smith, R. (2015) Utilising Hidden Markov Modelling for the Assessment of Accommodation in Conversational Speech. In: 18th International Congress of Phonetic Sciences, Glasgow, UK, 10-14 Aug 2015, ISBN 9780852619414

[img]
Preview
Text
109761.pdf - Published Version
Available under License Creative Commons Attribution No Derivatives.

153kB

Publisher's URL: http://www.icphs2015.info/Default.aspx

Abstract

The work presented here suggests a method for assessing speech accommodation in a holistic acoustic manner by utilising Hidden Markov Models (HMMs). The rationale for implementation of this method is presented along with an explanation of how HMMs work. Here, a heavily simplified HMM is used (single state; mixture of gaussians) in order to assess the applicability of more sophisticated HMMs. Results are presented from a small-scale study of six pairs of female Scottish-English speakers, showing measurement of significant trends and changes in holistic acoustic features of speakers during conversational interaction. Our findings suggest that methods integrating HMMs with current holistic acoustic measures of speech may be a useful tool in accounting for acoustic change due to speaker interaction.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Smith, Dr Rachel and Vinciarelli, Professor Alessandro and Stuart-Smith, Professor Jane
Authors: Solanki, V., Vinciarelli, A., Stuart-Smith, J., and Smith, R.
Subjects:P Language and Literature > P Philology. Linguistics
P Language and Literature > PE English
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
College/School:College of Arts & Humanities > School of Critical Studies > English Language and Linguistics
ISBN:9780852619414
Copyright Holders:Copyright © 2015 The Authors
Publisher Policy:Reproduced under a Creative Commons License
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record