Soft-Target Training with Ambiguous Emotional Utterances for DNN-Based Speech Emotion Classification
Atsushi Ando, Satoshi Kobashikawa, Hosana Kamiyama, Ryo Masumura, Yusuke Ijima, Yushi Aono
Abstract
This paper presents a novel emotion classification method for natural speech. One of the problems in the state-of-the-art method based on Deep Neural Network (DNN) is the paucity of the training data compared to model complexity. To solve this problem, this paper utilizes the ambiguous emotional utterances, utterances that have no dominant target emotion label. While previous work ignored ambiguous emotional utterances for training, the proposed method leverages all annotated labels via soft-target training. In addition, this paper modifies the soft-target training in order to effectively handle both clear and ambiguous emotional utterances. Experiments show that the proposed method yields performance improvements in terms of both weighted and unweighted accuracies.
BibTeX
@inproceedings{icassp2018_softtargettraini,
title = {Soft-Target Training with Ambiguous Emotional Utterances for DNN-Based Speech Emotion Classification},
author = {Atsushi Ando and Satoshi Kobashikawa and Hosana Kamiyama and Ryo Masumura and Yusuke Ijima and Yushi Aono},
booktitle = {ICASSP 2018},
year = {2018}
}