Visual comparison of speaker groups

Conference contribution
(Conference Contribution)

Publication Details

Author(s): Wankerl S, Hönig F, Batliner A, Orozco Arroyave J, Nöth E
Publisher: International Speech and Communication Association
Publication year: 2015
Pages range: 2613-2614


We describe a generic tool for visualising differences between two groups of speakers who produce a given word sequence. We do this by first time-aligning all recordings and then aggregating time-varying information within each group. By that, we can display prototypical loudness and tempo contours, and also spectrograms, together with information on variability and group effect size over time. An optional user-supplied segmentation (just needed for one of the recordings) can be used to relate local differences to individual phonemes. The system is validated with a group of speakers with Parkinson's disease and an age-matched control group. It will be provided as an opensource software package to the community.

FAU Authors / FAU Editors

Batliner, Anton Dr. phil.
Lehrstuhl für Informatik 5 (Mustererkennung)
Hönig, Florian
Lehrstuhl für Informatik 5 (Mustererkennung)
Nöth, Elmar Prof. Dr.-Ing.
Professur für Informatik (Mustererkennung)
Orozco Arroyave, Juan
Lehrstuhl für Informatik 5 (Mustererkennung)

How to cite

Wankerl, S., Hönig, F., Batliner, A., Orozco Arroyave, J., & Nöth, E. (2015). Visual comparison of speaker groups. (pp. 2613-2614). International Speech and Communication Association.

Wankerl, Sebastian, et al. "Visual comparison of speaker groups." Proceedings of the 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 International Speech and Communication Association, 2015. 2613-2614.


Last updated on 2018-19-04 at 03:20