A Speech-to-Knowledge-Graph Construction System
Abstract
This paper presents a HAO-Graph system that generates and visualizes knowledge graphs from a speech in real-time. When a user speaks to the system, HAO-Graph transforms the voice into knowledge graphs with key phrases from the original speech as nodes and edges. Different from language-to-language systems, such as Chinese-to-English and English-to-English, HAO-Graph converts a speech into graphs, and is the first of its kind. The effectiveness of our HAO-Graph system is verified by a two-hour chairman's talk in front of two thousand participants at an annual meeting in the form of a satisfaction survey.
Cite
Text
Fu et al. "A Speech-to-Knowledge-Graph Construction System." International Joint Conference on Artificial Intelligence, 2020. doi:10.24963/IJCAI.2020/777Markdown
[Fu et al. "A Speech-to-Knowledge-Graph Construction System." International Joint Conference on Artificial Intelligence, 2020.](https://mlanthology.org/ijcai/2020/fu2020ijcai-speech/) doi:10.24963/IJCAI.2020/777BibTeX
@inproceedings{fu2020ijcai-speech,
title = {{A Speech-to-Knowledge-Graph Construction System}},
author = {Fu, Xiaoyi and Zhang, Jie and Yu, Hao and Li, Jiachen and Chen, Dong and Yuan, Jie and Wu, Xindong},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2020},
pages = {5303-5305},
doi = {10.24963/IJCAI.2020/777},
url = {https://mlanthology.org/ijcai/2020/fu2020ijcai-speech/}
}