INTERSPEECH 2015
16th Annual Conference of the International Speech Communication Association

Dresden, Germany
September 6-10, 2015

Visual Comparison of Speaker Groups

Sebastian Wankerl, Florian Hönig, Anton Batliner, J. R. Orozco-Arroyave, Elmar Nöth

FAU Erlangen-Nürnberg, Germany

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 open-source software package to the community.

Full Paper

Bibliographic reference.  Wankerl, Sebastian / Hönig, Florian / Batliner, Anton / Orozco-Arroyave, J. R. / Nöth, Elmar (2015): "Visual comparison of speaker groups", In INTERSPEECH-2015, 2613-2614.