Blog
-- Thoughts on data analysis, software
development and innovation management. Comments are welcome
Post 26
Emotion detection using both acoustic and linguistic information in children's speech
27-Oct-2009
Dr. Michael Wagner, director of the National Center for Biometric Studies at the
University of Canberra, Australia, has given a speech on emotion analysis at UPC.
He has presented their contribution to the Emotion Challenge that was held last
September at Interspeech. They proposed the fusion of acoustic and linguistic
features in order to detect emotion states in children's speech.
He has proposed the acquisition of a host of acoustic features to get the most out
of the plain speech signal, an approach he himself has criticized for being
unscientific. With respect to the linguistic characterization of speech they
detected a list of emotionally salient words and compared its decision with the
one provided by the acoustic module. Although his publication did not win the
challenge, their approach is very interesting and innovative
since they were the only participating team that considered linguistic features.
|
All contents © Alexandre Trilla 2008-2025 |