@inproceedings{3fbabd80b3ec432b9fe92b7a156508fb,
title = "Speech2Stroke: Generate Chinese Character Strokes Directly from Speech",
abstract = "Chinese character is composed of spatial arrangement of strokes. A portion of these strokes combines to form phonetic component, which provides a clue to the pronunciation of the entire character, the others combine to form semantic component, which indicates semantic level information for speech context. How closely the connection between the internal strokes of Chinese characters and speech? In this paper, we propose Speech2Stroke, a end-to-end model that exploits the phonetic and morphologic level information of pictographic words. Specifically, we generate strokes directly from the speech by Speech2Stroke. The performance of Speech2Stroke is evaluated by the specific stroke error rate(SER). The SER of the optimal model can achieve 20.61\%. Through the experiments and analysis, we show that our model has the ability to capture the alignment between audio and the internal structures of pictographic characters.",
keywords = "Deep learning, Pictographic word, Stroke of Chinese character",
author = "Yinhui Zhang and Wei Xi and Zhao Yang and Sitao Men and Rui Jiang and Yuxin Yang and Jizhong Zhao",
note = "Publisher Copyright: {\textcopyright} 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.; 16th EAI International Conference on Collaborative Computing: Networking, Applications, and Worksharing, CollaborateCom 2020 ; Conference date: 16-10-2020 Through 18-10-2020",
year = "2021",
doi = "10.1007/978-3-030-67537-0\_6",
language = "英语",
isbn = "9783030675363",
series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "83--94",
editor = "Honghao Gao and Xinheng Wang and Muddesar Iqbal and Yuyu Yin and Jianwei Yin and Ning Gu",
booktitle = "Collaborative Computing",
}