Search

Your search keyword '"Li, Weiqin"' showing total 595 results
Start Over Author "Li, Weiqin" Search Limiters Full Text
595 results on '"Li, Weiqin"'

1. Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models

Author

Li, Weiqin, Yang, Peiji, Zhong, Yicheng, Zhou, Yixuan, Wang, Zhisheng, Wu, Zhiyong, Wu, Xixin, and Meng, Helen

Subjects
Computer Science - Sound, Computer Science - Computation and Language, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Spontaneous style speech synthesis, which aims to generate human-like speech, often encounters challenges due to the scarcity of high-quality data and limitations in model capabilities. Recent language model-based TTS systems can be trained on large, diverse, and low-quality speech datasets, resulting in highly natural synthesized speech. However, they are limited by the difficulty of simulating various spontaneous behaviors and capturing prosody variations in spontaneous speech. In this paper, we propose a novel spontaneous speech synthesis system based on language models. We systematically categorize and uniformly model diverse spontaneous behaviors. Moreover, fine-grained prosody modeling is introduced to enhance the model's ability to capture subtle prosody variations in spontaneous speech.Experimental results show that our proposed method significantly outperforms the baseline methods in terms of prosody naturalness and spontaneous behavior naturalness., Comment: Accepted by INTERSPEECH 2024

Published
2024

2. Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis

Author

Li, Weiqin, Lei, Shun, Huang, Qiaochu, Zhou, Yixuan, Wu, Zhiyong, Kang, Shiyin, and Meng, Helen

Subjects
Computer Science - Sound, Computer Science - Computation and Language, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the high cost of labeling spontaneous behavior. In this paper, we propose a semi-supervised pre-training method to increase the amount of spontaneous-style speech and spontaneous behavioral labels. In the process of semi-supervised learning, both text and speech information are considered for detecting spontaneous behaviors labels in speech. Moreover, a linguistic-aware encoder is used to model the relationship between each sentence in the conversation. Experimental results indicate that our proposed method achieves superior expressive speech synthesis performance with the ability to model spontaneous behavior in spontaneous-style speech and predict reasonable spontaneous behavior from text., Comment: Accepted by INTERSPEECH 2023

Published
2023

3. GTN-Bailando: Genre Consistent Long-Term 3D Dance Generation based on Pre-trained Genre Token Network

Author

Zhuang, Haolin, Lei, Shun, Xiao, Long, Li, Weiqin, Chen, Liyang, Yang, Sicheng, Wu, Zhiyong, Kang, Shiyin, and Meng, Helen

Subjects
Computer Science - Sound, Computer Science - Multimedia, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Music-driven 3D dance generation has become an intensive research topic in recent years with great potential for real-world applications. Most existing methods lack the consideration of genre, which results in genre inconsistency in the generated dance movements. In addition, the correlation between the dance genre and the music has not been investigated. To address these issues, we propose a genre-consistent dance generation framework, GTN-Bailando. First, we propose the Genre Token Network (GTN), which infers the genre from music to enhance the genre consistency of long-term dance generation. Second, to improve the generalization capability of the model, the strategy of pre-training and fine-tuning is adopted.Experimental results on the AIST++ dataset show that the proposed dance generation framework outperforms state-of-the-art methods in terms of motion quality and genre consistency., Comment: Accepted by ICASSP2023.Demo page: https://im1eon.github.io/ICASSP23-GTNB-DG/

Published
2023

8. Correlation between protoporphyrin Ⅸ and hepatitis, cirrhosis, and liver cancer

Author

WANG Xia, CUI Jie, LIU Mi, LI Weiqin, and LIU Kaige

Subjects
chronic hepatitis b, liver cirrhosis, liver cancer, protoporphyrin ⅸ, cholestasis, liver function damage, Medicine
Abstract

Objective To investigate the clinical significance of protoporphyrin Ⅸ (PPⅨ) in different stages of liver disease development, including hepatitis, cirrhosis, and liver cancer. Methods A total of 41 patients with chronic hepatitis (hepatitis group), 33 patients with liver cirrhosis (cirrhosis group), and 19 patients with liver cancer (liver cancer group) who visited the First Affiliated Hospital of Xi'an Medical University from January 2022 to December 2022 were selected as study object. Additionally, 40 healthy examinees during the same period were selected as the health control group. The basic information, blood routine, liver function, coagulation function, alpha fetoprotein (AFP)，controlled attenuation parameter (CAP)，liver stiffness measurement (LSM)，γ-glutamyl transpeptidase to platelet ratio (GPR) from each group were collected and compared. The correlation between various indicators and PPⅨ was analyzed. And the predictive value of PPⅨ and liver function related indicators on liver stiffness was analyzed. Results There were significant differences in gender, age, and PPⅨ between the hepatitis group, liver cirrhosis group, and liver cancer group compared to the control group (P

Published
2023
Full Text
View/download PDF

15. Region-Manipulated Fusion Networks for Pancreatitis Recognition

Author

Wang, Jian, Li, Xiaoyao, Shu, Xiangbo, and Li, Weiqin

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

This work first attempts to automatically recognize pancreatitis on CT scan images. However, different form the traditional object recognition, such pancreatitis recognition is challenging due to the fine-grained and non-rigid appearance variability of the local diseased regions. To this end, we propose a customized Region-Manipulated Fusion Networks (RMFN) to capture the key characteristics of local lesion for pancreatitis recognition. Specifically, to effectively highlight the imperceptible lesion regions, a novel region-manipulated scheme in RMFN is proposed to force the lesion regions while weaken the non-lesion regions by ceaselessly aggregating the multi-scale local information onto feature maps. The proposed scheme can be flexibly equipped into the existing neural networks, such as AlexNet and VGG. To evaluate the performance of the propose method, a real CT image database about pancreatitis is collected from hospitals \footnote{The database is available later}. And experimental results on such database well demonstrate the effectiveness of the proposed method for pancreatitis recognition.

Published
2019

17. Association between pretreatment lymphocyte count and efficacy of immune-enhancing therapy in acute necrotising pancreatitis: a post-hoc analysis of the multicentre, randomised, placebo-controlled TRACE trial

Author

Ke, Lu, Mao, Wenjian, Zhou, Jing, Xu, Minyi, Jiang, Wendi, Zhang, He, Lin, Jiajia, Lu, Mengjie, Chen, Yan, Ma, Mingmin, Li, Gang, Ye, Bo, Li, Baiqiang, Tong, Zhihui, Liu, Yuxiu, Li, Weiqin, Shao, Fang, Chen, Tao, Lv, Nonghua, Zhu, Yin, Xia, Liang, He, Wenhua, Zhenping, Chen, Pan, Xinting, Zhu, Qingyun, Wan, Youdong, Mei, Hong, Li, Kang, Chen, Miao, He, Chengjian, Yao, Hongyi, Zhu, Zigui, Gu, Weili, Lu, Weihua, Wu, Jingyi, Zhou, Feng, Tu, Shumin, Fu, Long, Xue, Bingg, Ni, Haibin, Huang, Xiaofei, Zhou, Dandan, Zhang, Guoxiu, Ren, Lening, Li, Dahuan, Zhao, Xiangyang, Zhao, Wei, Chen, Xiaomei, Sun, Junli, Xin, Keke, Chen, Weiwei, Xu, Qingcheng, Song, Jingchun, Zeng, Qingbo, Shao, Min, Zhao, Dongsheng, Tu, Jianfeng, Yang, Honggup, Windsor, John, and Ma, Penglin

Published
2023
Full Text
View/download PDF

18. Circulating Lysophosphatidylcholines in Early Pregnancy and Risk of Gestational Diabetes in Chinese Women.

Author

Liu, Jinnan, Li, Jing, Li, Sainan, Leng, Junhong, Li, Weiqin, Yang, Wen, Huo, Xiaoxu, Chen, Liwei, Ma, Ronald CW, Hu, Gang, Fang, Zhongze, and Yang, Xilin

Subjects
Humans, Diabetes, Gestational, Lysophosphatidylcholines, Glucose Tolerance Test, Prognosis, Risk Factors, Case-Control Studies, Follow-Up Studies, Prospective Studies, Gestational Age, Pregnancy, Adult, China, Female, Chinese women, bile acids, gestational diabetes mellitus, metabolism, lysophosphatidylcholines, Clinical Sciences, Paediatrics and Reproductive Medicine, Endocrinology & Metabolism
Abstract

ObjectivesThis study aimed to explore associations of lysophosphatidylcholines (LPCs) in early pregnancy with gestational diabetes mellitus (GDM), and whether LPCs mediated the associations of bile acids with GDM risk or had interactive effects with bile acids on GDM risk.DesignWe conducted a 1:1 nested case-control study (n = 486) from a large prospective pregnant women cohort in urban Tianjin, China. Blood samples were collected at their first antenatal care visit (median at 10th gestational week). LPCs were measured by liquid chromatography-tandem mass spectrometry analysis. Conditional binary logistic regression and restricted cubic spline analysis were used to identify cutoff points of these metabolites for GDM risk.ResultsOf the 6 detectable LPCs, LPC14:0 less than 0.24 nmol/mL, LPC15:0 at 0.45 nmol/mL or greater, and LPC18:0 at 18.00 nmol/mL or greater were independently associated with GDM risk. Adjustment for LPC18:0 slightly attenuated odds ratios (ORs) of deoxycholic acid (DCA, ≤ 0.36 nmol/mL) and glycoursodeoxycholic acid (GUDCA, ≤ 0.07 nmol/mL) for GDM, and the correlations of DCA and GUDCA with LPC18:0 were weak. However, the presence of DCA at 0.36 nmol/mL or less greatly amplified the adjusted OR of LPC18:0 at 18.00 nmol/mL or greater alone for GDM from 8.18 (2.51-26.7) up to 17.7 (6.64-47.1), with significant additive interaction. Similarly, the presence of GUDCA at 0.07 nmol/mL or less also greatly amplified the adjusted OR of LPC18:0 at 18.00 nmol/mL or greater alone for GDM from 17.2 (1.77-168) up to 73.8 (12.7-429), with significant additive interaction.ConclusionsLPCs in early pregnancy were associated with GDM risk. Low DCA or GUDCA greatly amplified the effect of high LPC18:0 on GDM, and its molecular mechanism is worth further investigations.

Published
2020

24. Correction to: Actively implementing an evidence-based feeding guideline for critically ill patients (NEED): a multicenter, cluster-randomized, controlled trial

Author

Ke, Lu, Lin, Jiajia, Doig, Gordon S., van Zanten, Arthur R. H., Wang, Yang, Xing, Juan, Zhang, Zhongheng, Chen, Tao, Zhou, Lixin, Jiang, Dongpo, Shi, Qindong, Lin, Jiandong, Liu, Jun, Cheng, Aibin, Liang, Yafeng, Gao, Peiyang, Sun, Junli, Liu, Wenming, Yang, Zhenyu, Zhang, Rumin, Xing, Wei, Zhang, An, Zhou, Zhigang, Zhou, Tingfa, Liu, Yang, Tong, Fei, Wang, Qiuhui, Pan, Aijun, Huang, Xiaobo, Fan, Chuming, Lu, Weihua, Shi, Dongwu, Wang, Lei, Li, Wei, Gu, Liming, Xie, Yingguang, Sun, Rongqing, Guo, Feng, Han, Lin, Zhou, Lihua, Zheng, Xiangde, Shan, Feng, Liu, Jianbo, Ai, Yuhang, Qu, Yan, Li, Liandi, Li, Hailing, Pan, Zhiguo, Xu, Donglin, Zou, Zhiqiang, Gao, Yan, Yang, Chunli, Kou, Qiuye, Zhang, Xijing, Wu, Jinglan, Qian, Chuanyun, Zhang, Weixing, Zhang, Minjie, Zong, Yuan, Qin, Bingyu, Zhang, Fusen, Zhai, Zhe, Sun, Yun, Chang, Ping, Yu, Bo, Yu, Min, Yuan, Shiying, Deng, Yijun, Zhao, Liyun, Zang, Bin, Li, Yuanfei, Zhou, Fachun, Chen, Xiaomei, Shao, Min, Wu, Weidong, Wu, Ming, Zhang, Zhaohui, Li, Yimin, Guo, Qiang, Wang, Zhiyong, Gong, Yuanqi, Song, Yunlin, Qian, Kejian, Feng, Yongjian, Fu, Baocai, Liu, Xueyan, Li, Zhiping, Gong, Chuanyong, Sun, Cheng, Yu, Jian, Tang, Zhongzhi, Huang, Linxi, Ma, Biao, He, Zhijie, Zhou, Qingshan, Yu, Rongguo, Tong, Zhihui, and Li, Weiqin

Published
2022
Full Text
View/download PDF

25. Actively implementing an evidence-based feeding guideline for critically ill patients (NEED): a multicenter, cluster-randomized, controlled trial

Author

Ke, Lu, Lin, Jiajia, Doig, Gordon S., van Zanten, Arthur R. H., Wang, Yang, Xing, Juan, Zhang, Zhongheng, Chen, Tao, Zhou, Lixin, Jiang, Dongpo, Shi, Qindong, Lin, Jiandong, Liu, Jun, Cheng, Aibin, Liang, Yafeng, Gao, Peiyang, Sun, Junli, Liu, Wenming, Yang, Zhenyu, Zhang, Rumin, Xing, Wei, Zhang, An, Zhou, Zhigang, Zhou, Tingfa, Liu, Yang, Tong, Fei, Wang, Qiuhui, Pan, Aijun, Huang, Xiaobo, Fan, Chuming, Lu, Weihua, Shi, Dongwu, Wang, Lei, Li, Wei, Gu, Liming, Xie, Yingguang, Sun, Rongqing, Guo, Feng, Han, Lin, Zhou, Lihua, Zheng, Xiangde, Shan, Feng, Liu, Jianbo, Ai, Yuhang, Qu, Yan, Li, Liandi, Li, Hailing, Pan, Zhiguo, Xu, Donglin, Zou, Zhiqiang, Gao, Yan, Yang, Chunli, Kou, Qiuye, Zhang, Xijing, Wu, Jinglan, Qian, Chuanyun, Zhang, Weixing, Zhang, Minjie, Zong, Yuan, Qin, Bingyu, Zhang, Fusen, Zhai, Zhe, Sun, Yun, Chang, Ping, Yu, Bo, Yu, Min, Yuan, Shiying, Deng, Yijun, Zhao, Liyun, Zang, Bin, Li, Yuanfei, Zhou, Fachun, Chen, Xiaomei, Shao, Min, Wu, Weidong, Wu, Ming, Zhang, Zhaohui, Li, Yimin, Guo, Qiang, Wang, Zhiyong, Gong, Yuanqi, Song, Yunlin, Qian, Kejian, Feng, Yongjian, Fu, Baocai, Liu, Xueyan, Li, Zhiping, Gong, Chuanyong, Sun, Cheng, Yu, Jian, Tang, Zhongzhi, Huang, Linxi, Ma, Biao, He, Zhijie, Zhou, Qingshan, Yu, Rongguo, Tong, Zhihui, and Li, Weiqin

Published
2022
Full Text
View/download PDF

34. Design and Experimental Study of Banana Bunch Transportation Device with Lifting Mechanism and Automatic Bottom-Fixing Fruit Shaft.

Author

Li, Weiqin, Yang, Zhou, Xu, Xing, Li, Weixi, Mo, Xingkang, Yu, Jiaxiang, and Duan, Jieli

Subjects
AUTOMATIC control systems, DIELECTRIC loss, ANGULAR acceleration, ANGULAR velocity, ORCHARDS, BANANAS
Abstract

In addressing the challenges of high labor intensity, cost, and potential mechanical damage to banana fruit in orchards, this study presents the design of a banana bunch transport device featuring a lifting mechanism and an automatic fruit shaft bottom-fixing system. The device is tailored to the planting and morphological characteristics of banana bunches, aiming for efficient, low-loss, and labor-saving mechanized transport. Key design considerations included the anti-overturning mechanism and the lifting system based on transportation conditions and the physical dimensions of banana bunches. A dynamic simulation was conducted to analyze the angular velocity and acceleration during the initial conveying stages, forming the basis for the fruit shaft bottom-fixation mechanism. A novel horizontal multi-point scanning method was developed to accurately identify and secure the fruit shaft bottom, complemented by an automated control system. Experimental results showed a 95.83% success rate in identification and fixation, validated by field trials that confirmed the necessity and stability of the fixation mechanism. To enhance the durability of the fruit shaft bottom-fixation mechanism, a multi-factor test was conducted, optimizing the device's maximum travel speed and minimizing the banana bunch's oscillation angle. Field tests showed an oscillation angle of 8.961°, closely matching the simulated result of 9.526°, demonstrating the reliability of the response surface analysis model. This study offers a practical and efficient solution for banana bunch transport in orchards, showcasing significant practical value and potential for wider adoption. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results