“Demos”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第3行: 第3行:
 
We recorded an interesting video that show part of our research, have fun! [http://zhangmiao.cslt.org/实验室宣传.mov link]
 
We recorded an interesting video that show part of our research, have fun! [http://zhangmiao.cslt.org/实验室宣传.mov link]
  
<object id="MediaPlayer" classid="clsid:22D6F312-B0F6-11D0-94AB-0080C74C7E95" width="800" height="600" standby="Loading Windows Media Player components…" type="application/x-oleobject" codebase="http://activex.microsoft.com/activex/controls/mplayer/en/nsmp2inf.cab#Version=6,4,7,1112">
 
    <param name="FileName" value="实验室宣传.mov">
 
    <param name="AutoStart" value="true">
 
    <param name="ShowControls" value="true">
 
    <param name="BufferingTime" value="2">
 
    <param name="ShowStatusBar" value="true">
 
    <param name="AutoSize" value="true">
 
    <param name="InvokeURLs" value="false">
 
    <param name="AnimationatStart" value="1">
 
    <param name="TransparentatStart" value="1">
 
    <param name="Loop" value="1">
 
    <embed type="application/x-mplayer2" src="test.avi" name="MediaPlayer" autostart="1" showstatusbar="1" showdisplay="1" showcontrols="1" loop="0" videoborder3d="0" pluginspage="http://www.microsoft.com/Windows/MediaPlayer/" width="800" height="600"></embed>
 
  </object>
 
  
 
'''Speech Technology'''
 
'''Speech Technology'''

2018年4月10日 (二) 01:19的版本

Demo Video

We recorded an interesting video that show part of our research, have fun! link


Speech Technology

Tianxing.png

  • CSLT is collaborating with Sinovoice to develope its speech input app on mobiles. It is a free and open source package which supports various input methods including speech, pinyin and hand writting. We are supporting the kernel of ASR. It is a cloud-based LVCSR system that supports free speech input under complex acoustic environments. Download from Sinovoice.

Hcicloud-asr.png

  • A simple online demo for our speech recognition technology can be found in the HCI Cloud research center. Online demo from Sinvoice.


Speaker Technology

Shengmibao.png

  • CSLT collaborated with d-EAR to develope a fast and robust speaker recognition system based on random digit strings. download from d-EAR.


Language Technology