@misc{10481/55222,
year = {2018},
month = {11},
url = {http://hdl.handle.net/10481/55222},
abstract = {Personalized emotion recognition provides an individual training model for each target
user in order to mitigate the accuracy problem when using general training models collected from
multiple users. Existing personalized speech emotion recognition research has a cold-start problem
that requires a large amount of emotionally-balanced data samples from the target user when creating
the personalized training model. Such research is difficult to apply in real environments due to the
difficulty of collecting numerous target user speech data with emotionally-balanced label samples.
Therefore, we propose the Robust Personalized Emotion Recognition Framework with the Adaptive
Data Boosting Algorithm to solve the cold-start problem. The proposed framework incrementally
provides a customized training model for the target user by reinforcing the dataset by combining the
acquired target user speech with speech from other users, followed by applying SMOTE (Synthetic
Minority Over-sampling Technique)-based data augmentation. The proposed method proved
to be adaptive across a small number of target user datasets and emotionally-imbalanced data
environments through iterative experiments using the IEMOCAP (Interactive Emotional Dyadic
Motion Capture) database.},
organization = {This research was supported by an Institute for Information & Communications Technology Promotion
(IITP) grant funded by the Korean government (MSIT) (No. 2017-0-00655). This research was supported by the
MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support
program (IITP-2017-0-01629) supervised by the IITP (Institute for Information & communications Technology
Promotion). This research was supported by the MIST (Ministry of Science and ICT), Korea, under the National
Program for Excellence in SW supervised by the IITP (Institute for Information & communications Technology
Promotion) (2017-0-00093).},
publisher = {MDPI},
keywords = {Speech emotion recognition},
keywords = {Personalization},
keywords = {Machine learning},
keywords = {Data selection},
keywords = {Data augmentation},
title = {Adaptive Data Boosting Technique for Robust Personalized Speech Emotion in Emotionally-Imbalanced Small-Sample Environments},
author = {Bang, Jaehun and Hur, Taeho and Kim, Dohyeong and Huynh-The, Thien and Lee, Jongwon and Han, Yongkoo and Baños Legrán, Oresti and Kim, Jee-In and Lee, Sungyoung},
}