F-0-Noise-Robust Glottal Source and Vocal Tract Analysis Based on ARX-LF Model

doi:10.1109/TASLP.2021.3120585

	F-0-Noise-Robust Glottal Source and Vocal Tract Analysis Based on ARX-LF Model
	Li, Yongwei 1; Tao, Jianhua1,2,3 ; Erickson, Donna 4; Liu, Bin1 ; Akagi, Masato 5
发表期刊	IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
ISSN	2329-9290
	2021
卷号	29 页码:3375-3383
通讯作者	Tao, Jianhua(jhtao@nlpr.ia.ac.cn)
摘要	This paper proposes a robust automatic speech analysis method based on a source-filter model constructed of an Auto-Regressive eXogenous (ARX) model and the Liljencrants-Fant (LF) model. The proposed method estimates glottal source waveform and vocal tract shape parameters using an analysis-by-synthesis approach. Structurally, the first step is to initialize the glottal source parameters using the inverse filter method, and the second step is to simultaneously estimate the glottal source waveform and the vocal tract shape parameters using an analysis-by-synthesis approach with an iterative algorithm. The proposed method was verified on synthetic voices with different glottal noise (signal to noise ratio) from 0 dB to 50 dB and different fundamental frequency (F-0) from 80 Hz to 320 Hz levels. The results show that the proposed method achieved a much higher estimation accuracy than that of the state-of-the-art inverse filtering methods on both different glottal noise and different F-0 levels.
关键词	Speech recognition Iterative methods Production Estimation Brain modeling Shape Low-frequency noise Glottal source vocal tract source-filter model ARX-LF model
DOI	10.1109/TASLP.2021.3120585
关键词[WOS]	WAVE-FORM ; LINEAR PREDICTION ; EPOCH EXTRACTION ; FLOW
收录类别	SCI
语种	英语
资助项目	National Key Research & Development Plan of China[2017YFC0820602] ; National Natural Science Foundation of China (NSFC)[61831022] ; National Natural Science Foundation of China (NSFC)[61771472] ; National Natural Science Foundation of China (NSFC)[61773379] ; National Natural Science Foundation of China (NSFC)[61901473] ; Key Program of the Natural Science Foundation of Tianjin[18JCZDJC36300] ; JSPS KAKENHI[20H04207]
项目资助者	National Key Research & Development Plan of China ; National Natural Science Foundation of China (NSFC) ; Key Program of the Natural Science Foundation of Tianjin ; JSPS KAKENHI
WOS研究方向	Acoustics ; Engineering
WOS类目	Acoustics ; Engineering, Electrical & Electronic
WOS记录号	WOS:000717754300001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	语音识别与合成
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46531
专题	多模态人工智能系统全国重点实验室_智能交互
通讯作者	Tao, Jianhua
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100101, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100101, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence, Beijing 100101, Peoples R China 4.Haskins Labs Inc, New Haven, CT 06511 USA 5.Japan Adv Inst Sci & Technol, Grad Sch Adv Sci & Technol, Nomi, Ishikawa 9231292, Japan
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Li, Yongwei,Tao, Jianhua,Erickson, Donna,et al. F-0-Noise-Robust Glottal Source and Vocal Tract Analysis Based on ARX-LF Model[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2021,29:3375-3383.
APA	Li, Yongwei,Tao, Jianhua,Erickson, Donna,Liu, Bin,&Akagi, Masato.(2021).F-0-Noise-Robust Glottal Source and Vocal Tract Analysis Based on ARX-LF Model.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,29,3375-3383.
MLA	Li, Yongwei,et al."F-0-Noise-Robust Glottal Source and Vocal Tract Analysis Based on ARX-LF Model".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 29(2021):3375-3383.