Paper Info
Title
Improving The Prediction Of Therapist Behaviors In Addiction Counseling By Exploiting Class Confusions
Abstract
In this work we address the problem of joint prosodic and lexical behavioral annotation for addiction counseling. We expand on past work that employed Recurrent Neural Networks ( RNNs) on multimodal features by grouping and classifying subsets of classes. We propose two implementations: One is hierarchical classification, which uses the behavior confusion matrix to cluster similar classes and makes the prediction based on a tree structure. The second is a graph-based method which uses the result of the original classification just to find a certain subset of the most probable candidate classes, where the candidate sets of different predicted classes are determined by the class confusions. We make a second prediction with simpler classifier to discriminate the candidates. The evaluation shows that the strict hierarchical approach degrades performance, likely due to error propagation, while the graph-based hierarchy provides significant gains.
Year
DOI
Venue
2019
10.1109/icassp.2019.8682885
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
behavioral signal processing, multimodal, class confusions, class hierarchy, graph-based
Propagation of uncertainty,Confusion matrix,Pattern recognition,Task analysis,Computer science,Recurrent neural network,Feature extraction,Tree structure,Artificial intelligence,Classifier (linguistics),Hierarchy,Machine learning
Conference
ISSN
Citations 
PageRank 
1520-6149
0
0.34
References 
Authors
0
8
Name
Order
Citations
PageRank
Zhuohao Chen100.68
karan singla244.52
James Gibson3134.94
Dogan Can412810.64
Zac E Imel5135.53
David Atkins65512.28
Georgiou Panayiotis742855.79
Narayanan Shrikanth85558439.23