個人簡介
凌震華,男,1979年8月出生於安徽省合肥市。中國科學技術大學信號與信息處理專業博士,現任中國科學技術大學電子工程與信息科學系副教授、博士生導師。主要研究方向為語音信號處理。
教育經歷
2002年取得中國科學技術大學“電子信息工程”專業學士學位;
2005年獲得中國科學技術大學“信號與信息處理”專業碩士學位;
2008年獲得中國科學技術大學“信號與信息處理”專業博士學位;
2007年10月至2008 年4 月,由Marie Curie Early Stage Training 項目支持,赴英國愛丁堡大學語音技術研究中心進行學術訪問;
2008年7月進入中國科學技術大學博士後流動站/安徽科大訊飛信息科技股份有限公司博士後工作站從事博士後科研工作;
2011年3月起任中國科學技術大學電子工程與信息科學系副教授。
研究方向
凌震華的主要研究領域包括語音合成、語音編碼、聲音轉換等。先後作為主要技術人員參與“基於HMM模型的高表現力多語種語音合成技術”(國家863十一五專題課題)、“高表現力多語種韻律建模研究”(國家自然科學基金項目)、“多語言語音合成關鍵技術與套用產品開發”(國家863十一五重點項目子課題)等國家科研項目並承擔核心研究工作。作為項目負責人承擔的國家科研項目有 “基於合成語音質量評估的語音合成方法研究”(中國博士後科學基金項目)和“結合發音動作參數的統計建模語音合成方法研究”(國家自然科學基金青年科學基金項目)。 凌震華在圍繞語音合成的相關核心技術領域進行了近十年的深入研究,取得了一系列國際領先的研究成果,並對語音合成系統的實際性能提升與產業套用做出了積極貢獻。完成發明專利申請7項(2項已獲授權);參與了IEEE Transactions on Audio Speech and Language Processing以及ICASSP/Interspeech/ISCSLP等語音信號處理領域主流國際學術期刊與會議的論文評審工作。
發表論文
在國內外學術期刊與會議上發表學術論文共40餘篇,並獲得2010年IEEE Signal Processing Society Young Author Best Paper Award。近五年發表的第一作者論文如下:
[1] Zhen-hua ling, Zhi-Guo Wang, Li-Rong Dai, “Statistical Modeling of syllable-Level F0 Features for HMM-based Unit Selection Speech Synthesis”, in Proc. of ISCSLP, pp. 144-147, 2010.
[2] Zhen-Hua Ling, Yu Hu, and Li-Rong Dai, “Global Variance Modeling on the Log Power Spectrum of LSPs for HMM-based Speech Synthesis”, in Proc. of Interspeech, pp. 825-828, 2010.
[3] Zhen-Hua Ling, Korin Richmond, and Junichi Yamagishi, “HMM-based Text-to-Articulatory-Movement Prediction and Analysis of Critical Articulators”, in Proc. of Interspeech, pp. 2194-2197, 2010.
[4] Zhen-Hua Ling, Korin Richmond, and Junichi Yamagishi, “An analysis of HMM-based prediction of articulatory movements,” Speech Communication, vol. 52, no. 10, pp. 834-846, 2010.
[5] Zhen-Hua Ling, Korin Richmond, Junichi Yamagishi, and Ren-Hua Wang, “Integrating articulatory features into HMM-based parametric speech synthesis,” IEEE Transaction on Audio, Speech, and Language Processing, vol. 17, no. 6, 2009, pp. 1171-1185.
[6] Zhen-Hua Ling, Yu Hu, “An experimental study on the similarity performance of HMM-based parametric speech synthesis,” in Proc. of the 10th National Conference on Man-Machine Speech Communication, 2009.
[7] 凌震華, 王仁華, “基於統計聲學模型的單元挑選語音合成算法,” 模式識別與人工智慧, vol. 21, no. 3, 2008, pp. 280-284.
[8] Zhen-Hua Ling, Heng Lu, Guo-Ping Hu, Li-Rong Dai, and Ren-Hua Wang, “The ustc entry for Blizzard Challenge 2008,” in Proc. of Blizzard Challenge workshop, 2008.
[9] Zhen-Hua Ling, Korin Richmond, Junichi Yamagishi, and Ren-Hua Wang, “Articulatory control of HMM-based parametric speech synthesis driven by phonetic knowledge,” in Proc. of Interspeech, 2008, pp. 573-576.
[10] Zhen-Hua Ling, Wei Zhang, and Ren-Hua Wang, “Cross-stream dependency modeling for HMM-based speech synthesis,” in Proc. of ISCSLP, 2008, pp. 5-8.
[11] Zhen-Hua Ling, and Ren-Hua Wang, “Minimum unit selection error training for HMM-based unit selection speech synthesis system,” in Proc. of ICASSP, pp. 3949-3952, 2008.
[12] Zhen-Hua Ling, Long Qin, Heng Lu, Yu Gao, Li-Rong Dai, Ren-Hua Wang, Yuan Jiang, Zhi-Wei Zhao, Jin-Hui Yang, Jie Chen, and Guo-Ping Hu, “The USTC and iFlytek speech synthesis systems for Blizzard Challenge 2007,” in Proc. of Blizzard Challenge workshop, 2007.
[13] Zhen-Hua Ling, and Ren-Hua Wang, “HMM-based hierarchical unit selection combining Kullback-Leibler divergence with likelihood criterion,” in Proc. of ICASSP, 2007, pp. 1245-1248.
[14] Zhen-Hua Ling, Yi-Jian Wu, Yu-Ping Wang, Long Qin, and Ren-Hua Wang, “USTC system for Blizzard Challenge 2006 - an improved HMM-based speech synthesis method,” in Proc. of Blizzard Challenge workshop, 2006.
[15] Zhen-Hua Ling, and Ren-Hua Wang, “HMM-based unit selection using frame sized speech segments,” in Proc. of Interspeech, 2006, pp. 2034-2037.