中国科学院自动化研究所   设为首页   加入收藏  联系我们
 
English
网站首页     实验室概况     研究队伍     组织机构     学术交流     科研成果     人才培养     开放课题     创新文化     资源共享     联系我们
    学术讲座

Multilingual Speech Processing

模式识别学术大讲堂

Advanced Lecture Series in Pattern Recognition

    (TITLE)Multilingual Speech Processing

(SPEAKER)Prof. Tanja Shultz (University of Karlsruhe)

(CHAIR)Prof. Jianhua Tao

     (TIME):November 20(Thursday), 2014, 15:00 PM

    (VENUE):No.2 Conference Room (3rd floor), Intelligence Building

报告摘要(ABSTRACT):

After a short introduction into characteristics of the world's languages and their impact on speech processing, I will discuss the possibilities of sharing data and knowledge across languages for model and component building, such as multilingual bottleneck features and multilingual acoustic modeling based on Deep Neural Networks.  Further topics include speech recognition systems for code-switching speech, and tools for rapid language adaptation particularly in the context of under-resourced languages.

报告人简介(BIOGRAPHY):

Tanja Schultz received her Ph.D. and Masters in Computer Science from University of Karlsruhe, Germany in 2000 and 1995 respectively and passed the German state examination for teachers of Mathematics, Sports, and Educational Science from Heidelberg University, in 1990. 

She joined Carnegie Mellon University in Pittsburgh, Pennsylvania in 2000 and holds a position as Research Professor at the Language Technologies Institute. Since 2007 she is Full Professor at the Department of Informatics of the Karlsruhe Institute of Technology (KIT) in Germany. She directs the Cognitive Systems Lab, where her research activities focus on human-machine communication with a particular area of expertise on multilingual speech processing, and on human-centered human-machine interfaces based on biosignals, i.e. capturing, processing, and interpreting muscle and brain activity as well as motion.

Tanja Schultz received several awards for her work, such as the FZI price for an outstanding Ph.D. thesis in 2001, the Allen Newell Medal for Research Excellence from Carnegie Mellon for her contribution to Speech Translation and the ISCA best paper award for her publication on language independent acoustic modeling in 2002, the Plux Wireless award in 2011 for the development of Airwriting, the Alcatel-Lucent Research Award for Technical Communication in 2012, a Google Research Award and the Otto-Haxel Award in 2013, as well as several best paper awards. She is the author of more than 280 articles published in books, journals, and proceedings. Tanja Schultz is a member of the Society of Computer Science (GI) for more than 20 years, of the IEEE Computer Society, and the International Speech Communication Association ISCA, where she currently serves as elected president.

友情链接
 
中科院自动化研究所 模式识别国家重点实验室 事业单位  京ICP备14019135号-3
NLPR, INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES