报告题目：Speech to Singing Synthesis - Science meeting Art (语音到歌唱合成—科学与艺术的碰撞)
报 告 人：李海洲 教授（新加坡资讯通讯研究院Principal Scientist，人类语言技术部主任）
主 持 人：谢磊 教授/院长助理
Dr Haizhou Li is currently a Principal Scientist and Department Head of the Human Language Technology, co-Director of Baidu-I2R Research Centre at the Institute for Infocomm Research (I2R), Singapore. He is also a conjoint Professor at the School of Electrical Engineering and Telecommunications, University of New South Wales, Australia.
Dr Li has worked on speech and language technology in academia and industry since 1988. Prior to joining I2R, he taught in the University of Hong Kong, South China University of Technology, CRIN/INRIA France, and Nanyang Technological University. He was appointed as Research Manager in Apple-ISS Research Centre in 1996, Research Director in Lernout & Hauspie Asia Pacific in 1999, and Vice President in InfoTalk Corp. Ltd in 2001.
Dr Li's research interests include automatic speech recognition, natural language processing and information retrieval. Dr Li now serves as an Associate Editor of IEEE Transactions on Audio, Speech and Language Processing, ACM Transactions on Speech and Language Processing, Computer Speech and Language (Elsevier) and Springer International Journal of Social Robotics. He is an elected Board Member of the International Speech Communication Association (ISCA, 2009-2013), an Executive Board Member of the Asian Federation of Natural Language Processing (AFNLP, 2006-) and a Vice President of Asia Pacific Signal and Information Processing Association (APSIPA, 2012-2013). Dr Li was appointed the General Conference Chair of the 50th Annual Meeting of the Association for Computational Linguistics (ACL 2012) and the 15th Annual Conference of ISCA (INTERSPEECH 2014). He was the recipient of National Infocomm Award of Singapore in 2001. He was named one of the two Nokia Professors 2009 by Nokia Foundation in recognition of his contribution to speaker and language recognition technologies.
Speech is the most natural way of human communication. With the advancement of digital signal processing and computer science, we are now able to manipulate human voice in different ways. There are three basic elements in human speech, namely, the phonetic content, the quality of voice or timbre, and the prosody. This talk will introduce a new technology, speech-to-singing, that automatically converts human speech to singing voice by keeping the speaker's voice timbre unchanged. With the help of speech-to-singing technology, everyone who can speak now becomes a good singer!