Multi-feature deep supervised voiceprint adversarial network for depression recognition from speech

doi:10.1016/j.bspc.2023.105704

	Multi-feature deep supervised voiceprint adversarial network for depression recognition from speech
	Pan, Yuchen 1; Shang, Yuanyuan 1,4; Wang, Wei 1,2; Shao, Zhuhong 1,5; Han, Zhuojin 1; Liu, Tie 1,5; Guo, Guodong 3; Ding, Hui 1,5
	2024-03-01
发表期刊	BIOMEDICAL SIGNAL PROCESSING AND CONTROL
ISSN	1746-8094
卷号	89 页码:15
摘要	Depression can induce a range of physiological effects, leading to notable distinctions in the acoustic charac-teristics exhibited by individuals with depression as opposed to those without. Designing efficient algorithms to accurately identify depression through speech poses a formidable challenge. In this paper, we propose the Multi-Feature Deep Supervised Voiceprint Adversarial Network (MFDS-VAN) for audio-based depression recognition. The MFDS-VAN assimilates extracted acoustic features and the audio waveform, subsequently generating predictions regarding the depression score. In order to attain more robust and discriminative spatial- temporal features associated with depression, the Encoding Network module merges long-term and short-term acoustic features with the unprocessed audio waveform, while the Regression Network module enables prediction of the depression score. The Deep Supervised Regression algorithm is designed by combining GE2E clustering and Huber regression for better network optimization. Furthermore, to enhance the representation the MFDS-VAN while diminishing the influence of individual voiceprint information, we propose the Voiceprint Adversarial Network. Experimental results conducted on AVEC 2013, AVEC 2014, and AVEC 2017 datasets demonstrate that the MFDS-VAN significantly enhances robustness and performance in speech-based depression recognition. Our model achieves competitive results when compared to recent audio-based methodologies.
关键词	Adversarial learning Audio processing Attention mechanism Deep neural network Depression recognition Feature enhancement
DOI	10.1016/j.bspc.2023.105704
收录类别	SCI
语种	英语
资助项目	National Natural Science tion of China[61876112] ; National Natural Science tion of China[61601311] ; Natural Science tion of Beijing, China[L201022]
WOS研究方向	Engineering
WOS类目	Engineering, Biomedical
WOS记录号	WOS:001116988300001
出版者	ELSEVIER SCI LTD
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://119.78.100.204/handle/2XEOYT63/38490
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shang, Yuanyuan; Wang, Wei
作者单位	1.Capital Normal Univ, Coll Informat Engn, Beijing 100048, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100000, Peoples R China 3.West Virginia Univ, Lane Dept Comp Sci & Elect Engn, Morgantown, WV 26506 USA 4.Beijing Adv Innovat Ctr Imaging Technol, Beijing 100048, Peoples R China 5.Beijing Key Lab Elect Syst Reliabil Technol, Beijing 100048, Peoples R China
推荐引用方式 GB/T 7714	Pan, Yuchen,Shang, Yuanyuan,Wang, Wei,et al. Multi-feature deep supervised voiceprint adversarial network for depression recognition from speech[J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL,2024,89:15.
APA	Pan, Yuchen.,Shang, Yuanyuan.,Wang, Wei.,Shao, Zhuhong.,Han, Zhuojin.,...&Ding, Hui.(2024).Multi-feature deep supervised voiceprint adversarial network for depression recognition from speech.BIOMEDICAL SIGNAL PROCESSING AND CONTROL,89,15.
MLA	Pan, Yuchen,et al."Multi-feature deep supervised voiceprint adversarial network for depression recognition from speech".BIOMEDICAL SIGNAL PROCESSING AND CONTROL 89(2024):15.