Quantification of segmentation and F0 errors and their effect on emotion recognition

Steidl S, Batliner A, Nöth E, Hornegger J (2008)

Publication Type: Authored book, Volume of book series

Publication year: 2008

Journal

Original Authors: Steidl S., Batliner A., Nöth E., Hornegger J.

Publisher: Springer-verlag

City/Town: Berlin

Book Volume: null

Pages Range: 525-534

Event location: Brno

Journal Issue: null

DOI: 10.1007/978-3-540-87391-4_67

Abstract

Prosodic features modelling pitch, energy, and duration play a major role in speech emotion recognition. Our word level features, especially duration and pitch features, rely on correct word segmentation and F0 extraction. For the FAU Aibo Emotion Corpus, the automatic segmentation of a forced alignment of the spoken word sequence and the automatically extracted F0 values have been manually corrected. Frequencies of different types of segmentation and F0errors are given and their influence on emotion recognition using different groups of prosodic features is evaluated. The classification results show that the impact of these errors on emotion recognition is small. © 2008 Springer-Verlag Berlin Heidelberg.

Authors with CRIS profile

How to cite

APA:

Steidl, S., Batliner, A., Nöth, E., & Hornegger, J. (2008). Quantification of segmentation and F0 errors and their effect on emotion recognition. Berlin: Springer-verlag.

MLA:

Steidl, Stefan, et al. Quantification of segmentation and F0 errors and their effect on emotion recognition. Berlin: Springer-verlag, 2008.

BibTeX: Download