![]()
Scientific Research
-
lingzhenhua,lingzhenhua.MODELING SPECTRAL ENVELOPES USING RESTRICTED BOLTZMANN MACHINES FOR
STATISTICAL PARAMETRIC SPEECH SYNTHESIS.2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL
PROCESSING (ICASSP),2012,7825-7829.
-
lingzhenhua,lingzhenhua.HMM-based hierarchical unit selection combining Kullback-Leibler
divergence with likelihood criterion.2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL
PROCESSING, VOL IV, PTS 1-3,2006,1245-+.
-
lingzhenhua,lingzhenhua.Waveform Modeling and Generation Using Hierarchical Recurrent Neural
Networks for Speech Bandwidth Extension.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2018,26(5):883-894.
-
lingzhenhua.Statistical parametric speech synthesis using a hidden trajectory model.SPEECH COMMUNICATION,2015,72149-159.
-
lingzhenhua.HMM-based unit selection speech synthesis using log likelihood ratios
derived from perceptual data.SPEECH COMMUNICATION,63-6427-37.
-
lingzhenhua,lingzhenhua.Minimum Kullback-Leibler Divergence Parameter Generation for HMM-Based
Speech Synthesis.IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2012,20(5):1492-1502.
-
顾佳宸 ,lingzhenhua,刘权,一种语境集合与回复集合的匹配方法及装置,201910411042.7,2019/08/16,
-
叶志秀 ,lingzhenhua,dailirong,一种少样本关系分类方法及系统,201910305007.7,2019/07/16,
-
陈谦 ,lingzhenhua,dailirong,一种融合单词语义知识的神经网络自然语言推理方法,201710842371.8,2018/01/12,
-
刘俊华 ,lingzhenhua,dailirong,基于动态剪枝束宽预测的语音识别效率优化方法,201610214520.1,2016/08/10,
-
高丽 ,lingzhenhua,陈凌辉,一种合成语音自然度的提升方法,201410828928.9,2015/04/01,
-
刘利娟 ,陈凌辉,lingzhenhua,dailirong,一种基于受限玻尔兹曼机的联合频谱建模的声音转换方法,201310360234.2,2013/11/27,2016/02/03.
-
基于深度学习的加密网络业务类型识别,进行,
-
高自然度语音合成技术研发,进行,
-
多语种语音合成关键技术,进行,
-
面向冬奥场景的多语种语音处理关键技术,进行,
-
面向语音合成的神经网络声码器研究,进行,
-
单声道语音增强方法的说话人标记研究项目,进行,
