Northwestern Polytechnical
Audio Speech & Language Processing Group
Digital Signal Processing
  • English
您是第counter free hit unique web位访客


Wireless Communications Speech Processing Medical Applications


      2014年6月9日,应谢磊教授邀请,新加坡资讯通信研究院(Institute of Infocomm Research, I2R)人类语言技术部语音分析与合成实验室主任董明会博士对西北工业大学计算机学院和陕西省语音与图像处理重点实验室进行了学术访问。当日下午16:00,董博士在计算机学院105学术报告厅做了题为“Singing voice synthesis research in I2R(新加坡资讯通信研究院在歌唱合成领域的研究进展)”的学术报告。报告会由谢磊教授主持,50余名师生参加了报告会。董博士为大家讲解了I2R在歌唱合成领域的研究进展,并为大家演示了基于Iphone手机开发的最新歌唱合成APP。报告会后,董博士与师生展开了讨论,同学们积极提问,受益匪浅。董博士访问期间,参观了陕西省语音与图像信息处理重点实验室在语音与音频处理、图像与视频处理等方面的研究成果,并同谢磊教授、付中华副教授等进行了深入讨论。

      目报告题目:Singing voice synthesis research in I2R(新加坡资讯通信研究院在歌唱合成领域的研究进展)

      报告人简介: Dr Minghui Dong is the Head of Voice Analysis and Synthesis Lab in Human Language Technology Department of Institute for Infocomm Research (I2R). He received BS, MS, and PhD from University of Science and Technology of China, Peking University, and National University of Singapore respectively. His research interests include speech and singing voice synthesis, voice conversion, natural language processing, speech recognition, etc. He was a research engineer from 1995 to 1998 at the Institute of Computer Science and Technology in Peking University (ICST,PKU) in China, where he worked on Chinese character recognition. From 2001 to 2004, he worked as a researcher in Infotalk Technology Pte Ltd (InfoTalk) in Singapore, where he did R&D work on text-to-speech systems. In Dec 2004, he joined the Institute for Infocomm Research (I2R). Here, he has been working on speech synthesis, voice conversion, singing voice processing, speech recognition and natural language processing. He is the vice president of Chinese and Oriental Languages Information Processing Society (COLIPS). He has been involved in organizing quite a few of international conferences. Recently, he is serving as Area Co-Chair in Speech Synthesis for Interspeech 2014, Program Co-Chair of International Symposium on Chinese Spoken Language Processing (ISCSLP) 2014, and Conference Chair of International Conference on Asian Language Processing (IALP) 2014.

      报告摘要: In this talk, I will first give a brief introduction of the voice synthesis work in I2R. Next I will focus on our latest work on singing voice synthesis. Singing is a way to express emotion. Many people like singing, but it need some skills to sing well. We are trying to generate nice singing voice with technology. Singing voice synthesis is an extended research topic of speech synthesis. Many of the research approaches for speech synthesis can be used in singing voice synthesis. However, singing has some unique features. Thus it needs to be handled differently in some way. This talk will cover our research work on singing pitch modelling, automatic harmonizer, speech2singing conversion, etc. A short demo will also be given as well.




  • 校园风光