教育经历：
(1) 2008-09 至 2013-12, 中国科学院自动化研究所, 模式识别与智能系统, 博士
(2) 2004-09 至 2008-06, 南京大学, 计算机科学与技术, 学士
科研与学术工作经历：
(1) 2016-10 至 今, 中国科学院自动化研究所, 数字内容技术与服务研究中心, 副研究员
(2) 2014-01 至 2016-09, 中国科学院自动化研究所, 数字内容技术与服务研究中心, 助理研究员

语音智能处理、多模态大模型

(1) 科技部, 新一代人工智能重大项目, 口语化语音识别与拟人化语音合成, 2020-11
至 2023-10, 465万元, 结题, 主持
(2) 科技部, 重点研发计划,  网络多媒体鉴伪关键技术研究之声纹鉴伪关键技术研究,
2020-07 至 2023-07, 132万元, 结题, 主持
(3) 科技部, 重点研发, QY20191603, 深度语义分析算法包, 2019-07 至 2023-06, 665万元, 结题, 参与
(4) 装备发展部, 预先研究项目, 小样本机器学习关键技术研究, 2021-08 至
2022-08, 150万元, 结题, 参与

1.Feng Yong,Cai Xinyuan,Ji Ruifang. Evaluation of the deep nonlinear metric learning based speaker identification  on the large scale of voiceprint corpus[C],2016.
2.Wang Geng,Wenfu Wang,Yuanyuan Zhao,et al. End-to-end Language Identification using Attention-based Recurrent Neural Networks[C],2016.
3.Jie Li,Heng Zhang,Xinyuan Cai,et al. Towards End-to-End Speech Recognition for Chinese Mandarin using Long Short-Term Memory Recurrent Neural Networks[C],2016.
4.Wang Geng,Yuanyan Zhao,Wenfu Wang,et al. Gating Recurrent Enhanced Memory Neural Networks on Language Identification[C],2016.
5.Wang Geng,Jie Li,,Shanshan Zhang,et al. Multilingual Tandem Bottleneck Feature For Language Identification[C],2016.
6.Li J,Zhang H,Cai XY,et al. Towards end-to-end speech recognition for Chinese Mandarin using long short-term memory recurrent neural networks[C],2015.
7.Xue Chen,Chunheng Wang,Baihua Xiao,et al. Scenario oriented discriminant analysis for still-to-video face recognition[C],2014:738-742.
8.Xue Chen,Chunheng Wang,Baihua Xiao,et al. Learning associate appearance manifolds for cross-pose face recognition[C],2014:1907-1911.
9.Xinyuan Cai,Chunheng Wang,Baihua Xiao,et al. Regularized latent least square regression for cross pose face recognition[C],2013:1247-1253.
10.Xue Chen,Baihua Xiao,Chunheng Wang,et al. Modular hierarchical feature learning with deep neural networks for face verification[C],2013:3690-3694.
11.Cai, Xinyuan,Wang, Chunheng,Xiao, Baihua,et al. Deep nonlinear metric learning with independent subspace analysis for face verification[C],2012:749-752.
12.Cai, Xinyuan,Wang, Chunheng,Xiao, Baihua,et al. ENVIRONMENT COUPLED METRICS LEARNING FOR UNCONSTRAINED FACE VERIFICATION[C],2012:577-580.
13.Cai, Xinyuan,Zhang, Rongguo,Xiao, Baihua,et al. Local binary pattern of maximum Gabor response: A novel face representation[C],2010:774-778.

肖柏华,张琳波,王春恒,等. 基于短语包模型的图像类别标注方法. CN201010195097.8[P]. 2010-05-31.
张琳波,肖柏华,王春恒,等. 基于级联式码本生成的图像分类方法. CN201010112508.2[P]. 2010-02-12.
王春恒,蔡新元,肖柏华,等. 一种基于隐最小二乘回归的多姿态人脸识别方法及其装置. CN103218609B.