Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System
Hiroaki Takatsu, Ryota Ando, Yoichi Matsuyama, Tetsunori Kobayashi
Abstract
As smart speakers and conversational robots become ubiquitous, the demand for expressive speech synthesis has increased. In this paper, to control the emotional parameters of the speech synthesis according to certain dialogue contents, we construct a news dataset with emotion labels (“positive,” “negative,” or “neutral”) annotated for each sentence. We then propose a method to identify emotion labels using a model combining BERT and BiLSTM-CRF, and evaluate its effectiveness using the constructed dataset. The results showed that the classification model performance can be efficiently improved by preferentially annotating news articles with low confidence in the human-in-the-loop machine learning framework.
BibTeX
@inproceedings{takatsu-etal-2020-sentiment,
title = "Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System",
author = "Takatsu, Hiroaki and
Ando, Ryota and
Matsuyama, Yoichi and
Kobayashi, Tetsunori",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.440/",
doi = "10.18653/v1/2020.coling-main.440",
pages = "5013--5025"
}