论文发表
课题组近年来在<<Speech Communications>>、美国声学学会会刊(JASA)、IEEE sensors Journal、ICASSP、INTERSPEECH等国内外刊物、国际会议发表相关文章100 余篇,其中在本领域重要SCI刊物发表论文40余篇。
Qingyang Hong, Lin Li, Jun Zhang, Lihong Wan, Huiyang Guo, "Transfer learning for PLDA-based speaker verification," Speech Communication, 92:90-99, 2017.
QingyangHong, Jun Zhang, Lin Li, Lihong Wan, Feng Tong, "A Transfer Learning Method for PLDA-based Speaker Verification," ICASSP 2016.[Code]
李 琳,万丽虹,洪青阳,张 君,李 明. 基于概率修正PLDA 的说话人识别系统. 天津大学学报,2015.8,48(8),pp.692-696.
李琳,万丽虹,洪青阳,张君,李明,基于概率修正PLDA的说话人识别技术,第十三届全国人机语音通讯学术会议(NCMMSC2015),2015年10月,中国,天津.
李琳,万丽虹,黄玲,洪青阳,张君,跨信道说话人识别语音库的设计与研究,第十三届全国人机语音通讯学术会议(NCMMSC2015),2015年10月,中国,天津.
江伟华,童峰,洪青阳,李琳,基于STM32的嵌入式语音增强系统,第十三届全国人机语音通讯学术会议(NCMMSC2015),2015年10月,中国,天津.
Qingyang Hong, Lin Li*, Ming Li, Ling Huang, Lihong Wan and Jun Zhang, "Modified-prior PLDA and Score Calibration for Duration Mismatch Compensation in Speaker Recognition System," INTERSPEECH 2015.
Qingyang Hong, Sheng Wang, and Zhijian Liu, "A Robust Speaker-Adaptive and Text-Prompted Speaker Verification System," p385-393, The 9th Chinese Conference on Biometric Recognition (CCBR 2014), Nov. 7-9, Shenyang, China.
F.Y.WU, F.Tong*, "Non-Uniform Constraint LMS algorithm for sparse system identification," IEEE communications Letters, Vol.17, 2013(2), pp385-388.
F.Y.WU, F.Tong*, "Gradient optimization p-norm-like constraint LMS algorithm for sparse system estimation," Signal Processing, Vol.93, 2013, pp967-971.
Ling Huang, Lin Li*, Shan He, "Speech enhancement base on sparse representation using universal dictionary," The 7th IEEE International Conference on Anti-counterfeiting,Security, and Identification, 2013, pp187-190.
S.X.Liu, F.Tong*, B.L.Luk, K.P.liu, "Fuzzy pattern recognition of impact acoustic signals for nondestructive evaluation," Sensors and Actuators A, Vol.167, 2011, pp588-593
F.Tong*, Xu Xiao Mei, Luk B. L, "Evaluation of tile-wall bonding integrity based on impact acoustics and support vector machine," SENSORS AND ACTUATORS A-PHYSICAL,Vol.144, 2008, pp97-104.
F.Tong, X.M.Xu, B.L.Luk, K.P.Liu, "Equalization of ultasonic transducers based on evolutionary algorithm and IIR lattice filter," Engineering Applications of Artificial Intelligence, Vol.21, 2008,1409-1415.
Q.Y. Hong and S. Kwong, "A Discriminative Training Approach for Text-independent Speaker Recognition," Signal Processing, Vol.85 (7), July 2005, pp. 1449-1463.
专利授权
团队在麦阵前端处理、声纹识别方面获13项发明专利,形成覆盖声源定位、抗混响、远场增强、后端识别等核心流程的前后端语音处理知识产权体系,另有8项专利申请已公开。
一种麦克风阵列远场语音增强装置(专利号:ZL 2017104091573)
基于声纹识别技术的亲情电话系统与亲情电话通讯方法(专利号:ZL 2010 1 0274490.6)
带声源方向跟踪功能的麦克风阵列语音增强装置及其方法(专利号:ZL 2012 1 0320004.9)
一种可抑制移动噪声的麦克风阵列语音增强装置(专利号:ZL 2012 1 0497016.9)
谱减与动态时间规整算法联合处理的抗噪声声纹识别装置(专利号:ZL 2013 1 0370030.7)
文本提示型声纹门禁系统(专利号:ZL 2013 1 0294975.5)
基于声纹识别技术的满意度调查作弊排查方法(专利号:ZL 2013 1 0754586.6)
具有主动降噪和辅助诊断功能的电子听诊器(专利号:ZL 2016 1 0027461.7)
一种混响条件下的麦克风阵列声源定位装置(专利号: ZL 2017104091501)
可适应强烈背景噪声的麦克风阵列语音增强装置(专利号:ZL 2016 1 0080236.X)
带相位自校正功能的声聚焦麦克风阵列长距离拾音装置(专利号:ZL 2016 1 0080008.2)
无直达声条件下的麦克风阵列语音增强装置(专利号:ZL 2017 1 0408164.1)
一种基于深度神经网络的多类声学特征整合方法和系统(专利号:ZL 202010073244.8)