Difference between revisions of "Xuewei Zhang 2016-04-18"

From cslt Wiki
Jump to: navigation, search
(以“* beamforming test :* reproduce DS beamforming (delay and sum beamforming) :* reproduce SD beamforming (super-directive beamforming) :* adjust the distance of micro...”为内容创建页面)
 
 
Line 2: Line 2:
 
:* reproduce DS beamforming (delay and sum beamforming)  
 
:* reproduce DS beamforming (delay and sum beamforming)  
 
:* reproduce SD beamforming (super-directive beamforming)
 
:* reproduce SD beamforming (super-directive beamforming)
:* adjust the distance of microphones or the location of source,test WER  [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=529 here]
+
:* adjust the distance of microphones or the location of source,test WER compared to WER from Jietong beamforming method [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=529 here]
 
* record in meeting room
 
* record in meeting room
 
* read papers
 
* read papers
 
:* HYBRID ACOUSTIC MODELS FOR DISTANT AND MULTICHANNEL LARGE VOCABULARY SPEECH RECOGNITION
 
:* HYBRID ACOUSTIC MODELS FOR DISTANT AND MULTICHANNEL LARGE VOCABULARY SPEECH RECOGNITION
 
:* FACTORED SPATIAL AND SPECTRAL MULTICHANNEL RAW WAVEFORM CLDNNS
 
:* FACTORED SPATIAL AND SPECTRAL MULTICHANNEL RAW WAVEFORM CLDNNS

Latest revision as of 00:55, 18 April 2016

  • beamforming test
  • reproduce DS beamforming (delay and sum beamforming)
  • reproduce SD beamforming (super-directive beamforming)
  • adjust the distance of microphones or the location of source,test WER compared to WER from Jietong beamforming method here
  • record in meeting room
  • read papers
  • HYBRID ACOUSTIC MODELS FOR DISTANT AND MULTICHANNEL LARGE VOCABULARY SPEECH RECOGNITION
  • FACTORED SPATIAL AND SPECTRAL MULTICHANNEL RAW WAVEFORM CLDNNS