Skip to main navigation Skip to search Skip to main content

Speech2Stroke: Generate Chinese Character Strokes Directly from Speech

  • Yinhui Zhang
  • , Wei Xi
  • , Zhao Yang
  • , Sitao Men
  • , Rui Jiang
  • , Yuxin Yang
  • , Jizhong Zhao
  • Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

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.

Original languageEnglish
Title of host publicationCollaborative Computing
Subtitle of host publicationNetworking, Applications and Worksharing - 16th EAI International Conference, CollaborateCom 2020, Proceedings
EditorsHonghao Gao, Xinheng Wang, Muddesar Iqbal, Yuyu Yin, Jianwei Yin, Ning Gu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages83-94
Number of pages12
ISBN (Print)9783030675363
DOIs
StatePublished - 2021
Event16th EAI International Conference on Collaborative Computing: Networking, Applications, and Worksharing, CollaborateCom 2020 - Shanghai, China
Duration: 16 Oct 202018 Oct 2020

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume349
ISSN (Print)1867-8211
ISSN (Electronic)1867-822X

Conference

Conference16th EAI International Conference on Collaborative Computing: Networking, Applications, and Worksharing, CollaborateCom 2020
Country/TerritoryChina
CityShanghai
Period16/10/2018/10/20

Keywords

  • Deep learning
  • Pictographic word
  • Stroke of Chinese character

Fingerprint

Dive into the research topics of 'Speech2Stroke: Generate Chinese Character Strokes Directly from Speech'. Together they form a unique fingerprint.

Cite this