Jangwon Kim, Prasanta Kumar Ghosh, Sungbok Lee, and Shrikanth S. Narayanan. A study of emotional information present in articulatory movements estimated using acoustic-to-articulatory inversion. In Proceedings of APSIPA Annual Summit and Conference, dec 2012.

Download

[PDF] 

Abstract

This study examines emotion-specific information (ESI) in the articulatory movements estimated using acousticto-articulatory inversion on emotional speech. We study two main aspects: (1) the degree of similarity between the pair of estimated and original articulatory trajectories for the same and different emotions and (2) the amount of ESI present in the estimated trajectory. They are evaluated using mean squared error between the articulatory pair and by automated emotion classification. This study uses parallel acoustic and articulatory data in 5 elicited emotions spoken by 3 native American English speakers. We also test emotion classification performance using articulatory trajectories estimated from different acoustic feature sets and they turn out subject-dependent. Experimental results suggest that the ESI in the estimated trajectory, although smaller than that in the direct articulatory measurements, is found to be complementary to that in the prosodic features and hence, suggesting the usefulness of estimated articulatory data for emotions research.

BibTeX Entry

@inproceedings{Kim2012Astudyofemotional,
 abstract = {This study examines emotion-specific information (ESI) in the articulatory movements estimated using acousticto-articulatory inversion on emotional speech. We study two main aspects: (1) the degree of similarity between the pair of estimated and original articulatory trajectories for the same and different emotions and (2) the amount of ESI present in the estimated trajectory. They are evaluated using mean squared error between the articulatory pair and by automated emotion classification. This study uses parallel acoustic and articulatory data in 5 elicited emotions spoken by 3 native American English speakers. We also test emotion classification performance using articulatory trajectories estimated from different acoustic feature sets and they turn out subject-dependent. Experimental results suggest that the ESI in the estimated trajectory, although smaller than that in the direct articulatory measurements, is found to be complementary to that in the prosodic features and hence, suggesting the usefulness of  estimated articulatory data for emotions research.},
 author = {Kim, Jangwon and Ghosh, Prasanta Kumar and Lee, Sungbok and Narayanan, Shrikanth S.},
 bib2html_rescat = {emotion},
 booktitle = {Proceedings of  APSIPA Annual Summit and Conference},
 keyword = {SPAN},
 link = {http://sail.usc.edu/publications/files/Kim-APSIPA2012.pdf},
 location = {Hollywood, CA},
 month = {dec},
 title = {A study of emotional information present in articulatory movements estimated using acoustic-to-articulatory inversion},
 year = {2012}
}

Generated by bib2html.pl (written by Patrick Riley ) on Tue Oct 17, 2017 10:45:56