Audiovisual classification of vocal outbursts in human conversation using long-short-term memory networksTools Eyben, F. and Petridis, S. and Schuller, Björn and Tzimiropoulos, Georgios and Zafeiriou, Stefanos and Pantic, Maja (2011) Audiovisual classification of vocal outbursts in human conversation using long-short-term memory networks. In: ICASSP 2011 - 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 22-27 May 2011, Prague, Czech Republic. Full text not available from this repository.AbstractWe investigate classification of non-linguistic vocalisations with a novel audiovisual approach and Long Short-Term Memory (LSTM) Recurrent Neural Networks as highly successful dynamic sequence classifiers. As database of evaluation serves this year's Paralinguistic Challenge's Audiovisual Interest Corpus of human-to-human natural conversation. For video-based analysis we compare shape and appearance based features. These are fused in an early manner with typical audio descriptors. The results show significant improvements of LSTM networks over a static approach based on Support Vector Machines. More important, we can show a significant gain in performance when fusing audio and visual shape features.
Actions (Archive Staff Only)
|
From the 1st Oct 2021, the research publications and student eTheses of University of Nottingham Ningbo China authors will be handled through the UNNC Research Information System (RIS).
If you are a UNNC author, please login to the UNNC RIS in order to deposit articles and etheses after this date, or contact UNNCRIS@nottingham.edu.cn if you have any enquiries in regard to this change.
If you are a UNNC author, please login to the UNNC RIS in order to deposit articles and etheses after this date, or contact UNNCRIS@nottingham.edu.cn if you have any enquiries in regard to this change.
Tools
Tools
