Comparison of HMM and TMDN Methods for Lip Synchronisation
G. Hofer, and K. Richmond. Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH), page 454-457. Makuhari, Japan, (September 2010)
Abstract
This paper presents a comparison between a hidden Markov model (HMM) based method and a novel artificial neural network (ANN) based method for lip synchronisation. Both model types were trained on motion tracking data, and a perceptual evaluation was carried out comparing the output of the models, both to each other and to the original tracked data. It was found that the ANN-based method was judged significantly better than the HMM based method. Furthermore, the original data was not judged significantly better than the output of the ANN method.
%0 Conference Paper
%1 Hofer2010
%A Hofer, Gregor
%A Richmond, Korin
%B Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH)
%C Makuhari, Japan
%D 2010
%K (HMM), Markov density hidden inversion lip mapping mixture model network, synchronisation,
%P 454-457
%T Comparison of HMM and TMDN Methods for Lip Synchronisation
%U http://www.isca-speech.org/archive/interspeech_2010/i10_0454.html
%X This paper presents a comparison between a hidden Markov model (HMM) based method and a novel artificial neural network (ANN) based method for lip synchronisation. Both model types were trained on motion tracking data, and a perceptual evaluation was carried out comparing the output of the models, both to each other and to the original tracked data. It was found that the ANN-based method was judged significantly better than the HMM based method. Furthermore, the original data was not judged significantly better than the output of the ANN method.
@inproceedings{Hofer2010,
abstract = {This paper presents a comparison between a hidden Markov model (HMM) based method and a novel artificial neural network (ANN) based method for lip synchronisation. Both model types were trained on motion tracking data, and a perceptual evaluation was carried out comparing the output of the models, both to each other and to the original tracked data. It was found that the ANN-based method was judged significantly better than the HMM based method. Furthermore, the original data was not judged significantly better than the output of the ANN method.},
added-at = {2021-02-01T10:51:23.000+0100},
address = {Makuhari, Japan},
author = {Hofer, Gregor and Richmond, Korin},
biburl = {https://www.bibsonomy.org/bibtex/265e659537c53ba799a413e939b657a9a/m-toman},
booktitle = {Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH)},
file = {:pdfs/hofer_interspeech_2010.pdf:PDF},
interhash = {706f99cc72a338dcab2f1245dfc57f7e},
intrahash = {65e659537c53ba799a413e939b657a9a},
keywords = {(HMM), Markov density hidden inversion lip mapping mixture model network, synchronisation,},
month = sep,
owner = {schabus},
pages = {454-457},
timestamp = {2021-02-01T10:51:23.000+0100},
title = {Comparison of {HMM} and {TMDN} Methods for Lip Synchronisation},
url = {http://www.isca-speech.org/archive/interspeech_2010/i10_0454.html},
year = 2010
}