[Adapt] Fwd: 触电论坛第六期《自动语音识别的深度学习及其应用》

Kenny Zhu kzhu at cs.sjtu.edu.cn
Mon Dec 17 08:58:32 CST 2012


Hi guys,

In case you are interested in deep learning, go to this tutorial, NOW!

Kenny

Begin forwarded message:

> From: Kai Yu <kai.yu at sjtu.edu.cn>
> Date: December 17, 2012 8:44:45 AM GMT+08:00
> To: "all at cs.sjtu.edu.cn" <all at cs.sjtu.edu.cn>
> Subject: Fwd: 触电论坛第六期《自动语音识别的深度学习及其应用》
> Reply-To: kai.yu at sjtu.edu.cn
> 
> 各位老师,今天微软研究院的俞栋来做一天的deep neural network的Tutorial,前面可能没有发到大家的手里,欢迎感兴趣的老师参加。
> 
> ---------- Forwarded message ----------
> From: 宋续明 
> Date: Wednesday, December 12, 2012
> Subject: 触电论坛第六期《自动语音识别的深入学习及其应用》
> To: 张小丽 <fashte at sjtu.edu.cn>, 卢建川 <lujianchuan at sjtu.edu.cn>, 叶一舟 <yyz45 at 126.com>, 叶冠豪 <5080109052 at sjtu.edu.cn>, 周云 <zhouyun19901001 at sjtu.edu.cn>, 杨敏霞 <wendyymx at gmail.com>, 王牧之 <wangmuzhi at sjtu.edu.cn>, 郭非 <guofei1988 at gmail.com>, 巢睿祺 <rickycrq at 126.com>, 季聿阶 <jiyujie880621 at gmail.com>, 吴俊 <reborn_w_j at 163.com>, 刘毓闻 <liuyuwen_sjtu at 126.com>, 王培丞 <wangpeicheng at sjtu.edu.cn>, 殷洁 <oursky2008 at sjtu.edu.cn>, 宋续明 <songxuming at sjtu.edu.cn>, 田怡萌 <tym at sjtu.edu.cn>, 李劲湘 <jx_li at sjtu.edu.cn>, 范儒 <fanru301 at sjtu.edu.cn>, 金晶 <jinjing at sjtu.edu.cn>, 林玲 <llin at sjtu.edu.cn>, 马丽丹 <malidan at sjtu.edu.cn>, 胡艳丽 <huyanli at sjtu.edu.cn>, 杨一帆 <yfyang at sjtu.edu.cn>, 王绍平 <spwang at sjtu.edu.cn>, 毛乾锟 <sonicmao123 at 163.com>, 郭相龙 <guoxianglong at sjtu.edu.cn>, 郭成鹏 <iidiot at sjtu.edu.cn>, 曾维娜 <molina at sjtu.edu.cn>, 陈家兴 <cjxjj2725 at yahoo.com.cn>, 薛秀珍 <xiuzhenxue at gmail.com>, 梁玉杰 <naughtyegg at 163.com>, 张楠 <nzhang312 at sina.com>
> Cc: 杨德祥 <bigydx at gmail.com>, 李帅波 <lishuaibo1989 at 163.com>, 俞凯 <kai.yu at sjtu.edu.cn>
> 
> 
> 
> 
> 各位老师,请帮忙通知所带同学~
>  
> 各位同学:
>        学生科协组织的触电论坛已到第六期,本期的论坛题目是 《自动语音识别的深入学习及其应用》,邀请的是微软的专家,时间是下周一(12月17日),地点是3-100,有素拓,分上午场和下午场,按两次讲座计算。计划参加的同学请与13日和14日到3-101c领取素拓。
>  
> Title: A Tutorial of Deep Learning and Its Applications in Automatic Speech Recognition
> 
> Speaker: 
> Dong Yu, Senior Researcher, Microsoft Research Redmond, U.S.
> 
> Time: 
> 09:30 - 12:00, Dec. 17 (Monday) 
> 14:00 - 16:00, Dec. 17 (Monday)
> 
> Venue:
> Electronic and Information Building 3#100, Shanghai Jiao Tong University
>  
> 
> Abstract:
> Recently, notable progress has been made in applying deep learning techniques to large vocabulary speech recognition (LVSR). In this tutorial I will describe the basic deep learning models, the intuition behind these models, and the reason deep neural network performs so well on LVSR. The tutorial consists of three parts. In the first part, I will introduce some basic philosophy that will help us understand deep models and related algorithms. In the second part, I will present the most popular deep learning models. In the third part, I will describe how deep neural networks can be used to improve LVSR and why such models have high potential.
> 
> Short Bio:
> Dr. Dong Yu joined Microsoft Corporation in 1998 and Microsoft Speech Research Group in 2002, where he is currently a senior researcher. He holds a Ph.D. degree in computer science from University of Idaho, an MS degree in computer science from Indiana University at Bloomington, an MS degree in electrical engineering from Chinese Academy of Sciences, and a BS degree (with honor) in electrical engineering from Zhejiang University. His current research interests include speech processing, robust speech recognition, discriminative training, and machine learning. He has published over 100 papers in these areas and is the inventor/coinventor of more than 40 granted/pending patents.
> His most recent work focuses on deep learning and its applications to large vocabulary speech recognition. The context-dependent deep neural network hidden Markov model (CD-DNN-HMM) he co-proposed and developed has been seriously challenging the dominant position of the conventional GMM based system for large vocabulary speech recognition. 
> Dr. Dong Yu is a senior member of IEEE. He is currently serving as a member of the IEEE Speech and Language Processing Technical Committee (2013-) and an associate editor of IEEE transactions on audio, speech, and language processing (2011-). He has served as an associate editor of IEEE signal processing magazine (2008-2011) and the lead guest editor of IEEE transactions on audio, speech, and language processing - special issue on deep learning for speech and language processing (2010-2011).
> 
> 
> 
> 
> 
> 
> 
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20121217/3a9cf932/attachment-0001.html>


More information about the Adapt mailing list