Publication Details
Brno University of Technology System for Interspeech 2010 Paralinguistic Challenge
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
Age- and gender-recognition, GMM, MMI, eigenvoice, fusion
This paper describes systems for the Age- and Gender-Sub-Challenges employ fusions of several sub-systems. We make use of our own acoustic frame-based feature sets
This paper describes Brno University of Technology (BUT) system for the Interspeech 2010 Paralinguistic Challenge. Our submitted systems for the Age- and Gender-Sub-Challenges employ fusions of several sub-systems. We make use of our own acoustic frame-based feature sets, as well as the provided utterance-based acoustic, prosodic and voice quality features. Modeling is based on Gaussian Mixture Models (GMM) and Support Vector Machines (SVM), followed by linear Gaussian backends and logistic regression-based fusion. For a single subsystem, we obtain improvement of about 2% absolute, for both tasks, on the development-set. Our final fusion results in nearly 9% absolute improvement for the Age task and about 4.5% for the Gender task on the development set. On the final test set we obtain 3.5% and 2% absolute improvement, respectively.
@inproceedings{BUT35025,
author="Marcel {Kockmann} and Lukáš {Burget} and Jan {Černocký}",
title="Brno University of Technology System for Interspeech 2010 Paralinguistic Challenge",
booktitle="Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)",
year="2010",
journal="Proceedings of Interspeech",
volume="2010",
number="9",
pages="2822--2825",
publisher="International Speech Communication Association",
address="Makuhari, Chiba",
isbn="978-1-61782-123-3",
issn="1990-9772",
url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/kockmann_interspeech2010_IS100567.pdf"
}