Title :
Contextual Hidden Markov Models
Author :
Radenen, Mathieu ; Artières, Thierry
Author_Institution :
LIP6, Univ. Pierre et Marie Curie, Paris, France
Abstract :
Multiple works have proposed extensions of HMMs for handling variability. We focus here on the design of HMMs whose probability distribution on sequences depends on additional external variables that we call the context, which may stand for emotion features in speech recognition, physical features in gesture recognition, etc. We show experimentally the relevance of the method for handwriting recognition.
Keywords :
emotion recognition; handwriting recognition; hidden Markov models; probability; speech recognition; HMM; contextual hidden Markov model; emotion feature; gesture recognition; handling variability; handwriting recognition; probability distribution; speech recognition; Context; Context modeling; Covariance matrix; Hidden Markov models; Speech recognition; Training; Vectors; Context variables; Handwriting Recognition; Hidden Markov Model;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6288328
