Study on Tibetan Speech Recognition Based on Ultrasonic Tongue Imaging, Lip Video and Audio

doi:10.1117/12.2656631

	Study on Tibetan Speech Recognition Based on Ultrasonic Tongue Imaging, Lip Video and Audio
	Zhang, JinXi; Li, ChunLing
	2022
会议名称	5th International Conference on Computer Information Science and Application Technology, CISAT 2022
会议录名称	Proceedings of SPIE - The International Society for Optical Engineering
卷号	12451
会议日期	July 29, 2022 - July 31, 2022
会议地点	Chongqing, China
会议录编者/会议主办者	Guangzhou Computer Society
出版者	SPIE
摘要	Speech recognition system is a pattern recognition system in essence, including feature extraction, pattern matching, reference pattern library and other three basic units.This paper implements a speech recognition system based on DNN-HMM structure with Kaldi toolkit. For multiple pronunciators, it can have synchronous acquisition of the tongue body morphology, lipping, pronunciation and other multiple physiological signals of Tibetan Lhasa dialect and process the data for feature extraction, model training, voice recognition, etc. The result shows that recognition results may vary according to different pronunciator models or articulation parts and the pronunciators of different articulation parts have low dependent recognition error rate but high independent recognition error rate. It also shows that ultrasonic tongue imaging and lip video image sequence includes pronunciator's acoustic feature information, which provide great significance for the study of voice recognition, particularly the speech synthesis and silent speech interface. © 2022 SPIE.
关键词	Feature extraction Medical imaging Pattern matching Physiological models Speech recognition Speech synthesis Error rate Extraction patterns Features extraction Lip video Recognition error Speech recognition systems Tibetan corpus Tibetans Utrasonic tongue imaging Voice and audio
DOI	10.1117/12.2656631
收录类别	EI
语种	英语
EI入藏号	20224713138860
EI主题词	Extraction
EI分类号	461.1 Biomedical Engineering ; 746 Imaging Techniques ; 751.5 Speech ; 802.3 Chemical Operations
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/33108
专题	商务传媒学院统计与数据科学学院
作者单位	Lanzhou University of Finance and Economics, Gansu, Lanzhou; 730020, China
推荐引用方式 GB/T 7714	Zhang, JinXi,Li, ChunLing. Study on Tibetan Speech Recognition Based on Ultrasonic Tongue Imaging, Lip Video and Audio[C]//Guangzhou Computer Society:SPIE,2022.