“ASR Status Report 2017-12-25”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“ {| class="wikitable" !Date!!People !! Last Week !! This Week !! Task Tracking |- | rowspan="8"|2017.12.18 |- |Ying Shi || * Finish the Voice-printer program *...”为内容创建页面)
 
第3行: 第3行:
 
!Date!!People !! Last Week !! This Week !! Task Tracking
 
!Date!!People !! Last Week !! This Week !! Task Tracking
 
|-
 
|-
| rowspan="8"|2017.12.18
+
| rowspan="8"|2017.12.25
  
  
第9行: 第9行:
 
|Ying Shi   
 
|Ying Shi   
 
||  
 
||  
* Finish the Voice-printer program
+
*  
* Apply the software copyright of Voice-printer
+
*  
* APSIPA 2017
+
 
||  
 
||  
* Finish the software copyright of Voice-checker
+
*
* Baseline of similar language recongnition system(i-vector, DNN, PTN)
+
*
 
||
 
||
 
* focus on function other than UI
 
* focus on function other than UI
第25行: 第24行:
 
|Lantian Li   
 
|Lantian Li   
 
||  
 
||  
* Optimize the demo of `VV_Seg` and `VV_QuickMark`.
+
* Complete the recipe for VV_FACTOR.
* Phone-aware scorning on deep speaker feature. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=643]
+
* 16K and 8K deep speaker model. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=643]
 
||
 
||
* Phone-aware scorning.
+
* Phonetic speaker embedding.
 
* Overlap training for speaker features.
 
* Overlap training for speaker features.
 
||  
 
||  
* test on trivial dataset
+
*  
 
|-
 
|-
  
第38行: 第37行:
 
|Zhiyuan Tang  
 
|Zhiyuan Tang  
 
||  
 
||  
* easy-to-read interfaces for Parrot
+
*  
 
||
 
||
* phone-level likelihood for detail diagnosis and an alpha version Parrot for test inside lab
+
*  
 
||
 
||
 
|-
 
|-

2017年12月25日 (一) 03:38的版本

Date People Last Week This Week Task Tracking
2017.12.25


Ying Shi
  • focus on function other than UI
  • i-vector LID first
Lantian Li
  • Complete the recipe for VV_FACTOR.
  • 16K and 8K deep speaker model. [1]
  • Phonetic speaker embedding.
  • Overlap training for speaker features.
Zhiyuan Tang