咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >Stabilization Improved Ultraso... 收藏
SSRN

Stabilization Improved Ultrasound Imaging Helmet Based on Skull Feature in the Articulatory Data Observation

作     者:Li, Yuxuan Wei, Jianguo Fang, Qiang Feng, Hui Yu, Hong Sun, Wenze Honda, Kiyoshi Wang, Lu Lu, Xugang 

作者机构:College of Intelligence and Computing Tianjin University Tianjin China Institute of Linguistics Chinese Academy of Social Sciences Beijing China School of Foreign Languages and Literature Tianjin University Tianjin China Nankai University Affiliated Maternity Hospital Nankai University Tianjin China College of Aeronautical Engineering Civil Aviation University of China Tianjin China Department of Orthodontics Tianjin Stomatological Hospital Nankai University Tianjin China Advanced Speech Technology Laboratory NICT Kyoto Japan 

出 版 物:《SSRN》 

年 卷 期:2023年

核心收录:

主  题:Ultrasonic imaging 

摘      要:The tongue is crucial for speech production because it determines vocal tract geometry. Ultrasonic imaging is one of the most popular methods for understanding the effect of articulatory motion on exploring the correlation between vocal tract configuration and audible sound. Imaging plane shift and contact variation are two key factors affecting the consistency of the obtained images. Our proposed study aims to tackle the issue of inconsistent imaging results caused by the above factors during recording by designing a helmet with skull morphology-oriented holders to keep the probe stable in the mid-sagittal plane. Its holders design takes advantage of the skull features of a human. For evaluating our work, ten subjects had to read the corpus in evaluation with two conditions: wearing our designed helmet and wearing a comparative headset. A sensor-based system is employed to help us evaluate our work on the imaging plane shift, contact variation, and the effects of the above factors on imaging quality. Compared to the comparative device, the imaging shift using our designed helmet is smaller than 1◦, the contact variation is decreased by about 49.8%, and the difference of the extracted tongue contours is decreased by about 50.0%. The imaging results present a consistent and regular trend. The above evaluations indicate that our designed helmet potentially provides trustworthy ultrasound imaging results for building a visual correlation cue of speech production. Moreover, we describe the helmet development process. © 2023, The Authors. All rights reserved.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分