ASR Status Report 2017-9-4 - 版本历史

2017年9月4日 (一) 05:22 Lilt

2017-09-04T05:22:11Z

2017年9月4日 (一) 02:56 Kangxf

2017-09-04T02:56:10Z

2017年9月4日 (一) 01:30 Zhangmiao

2017-09-04T01:30:08Z

2017年9月4日 (一) 01:29 Tanghui

2017-09-04T01:29:12Z

2017年9月4日 (一) 01:27 Zhangmiao

2017-09-04T01:27:25Z

2017年9月4日 (一) 01:24 Shiying

2017-09-04T01:24:17Z

2017年9月4日 (一) 01:23 Shiying

2017-09-04T01:23:36Z

2017年9月4日 (一) 01:19 Zhangmiao

2017-09-04T01:19:35Z

2017年9月4日 (一) 01:10 Tangzy

2017-09-04T01:10:22Z

Tangzy：以“{| class="wikitable" !Date!!People !! Last Week !! This Week |- | rowspan="9"|2017.8.21 |Jiayin Cai || * || * |- |- |Xiaofei Kang || * Recording new audios from...”为内容创建页面

2017-09-04T01:09:00Z

以“{| class="wikitable" !Date!!People !! Last Week !! This Week |- | rowspan="9"|2017.8.21 |Jiayin Cai || * || * |- |- |Xiaofei Kang || * Recording new audios from...”为内容创建页面

新页面

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="9"|2017.8.21

|Jiayin Cai
||
*
||
*
|-

|-
|Xiaofei Kang
||
* Recording new audios from 38 person, located in /work7/tanghui/kangxf/workspaces/speaker/wavdata/V2.0
* Improve the test website to judge before committing
||
* Test the new recording。
|-

|-
|Miao Zhang
||
*
||
*
|-

|-
|Yanqing Wang
||
* pruning the connections and refining, [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=626 results]
||
* Absent.
|-

|-
|Ying Shi
||
* check toolkit code
* multilingual baseline system
||
* train language id model
* use Lid to do multi-decoding
* some experiments for zhiyong zhang about TTS
|-

|-
|Yixiang Chen
||
*
||
*
|-

|-
|Lantian Li
||
* Attend IS2017.
||
* Go on speaker segmentation tasks.
|-

|-
|Zhiyuan Tang
||
* several indicators for VV scoring system, see [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a1/VV_scoring.pdf].
||
* more indicators, a demo with Shuai.
* toolbook writing.
|-

|}

------------------------

{| class="wikitable"
!Date!!People !! Last Week !! This Week
|-
| rowspan="8"|2017.8.21

|Xiaofei Kang
||
* Recording new audios from 38 person, located in /work7/tanghui/kangxf/workspaces/speaker/wavdata/V2.0
* Improve the test website to judge before committing
||
* Test the new recording。
|-

|-
|Miao Zhang
||
*
||
*
|-

|-
|Yanqing Wang
||
* pruning the connections and refining, [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=626 results]
||
* Absent.
|-

|-
|Ying Shi
||
* check toolkit code
* multilingual baseline system
||
* train language id model
* use Lid to do multi-decoding
* some experiments for zhiyong zhang about TTS
|-

|-
|Yixiang Chen
||
*
||
*
|-

|-
|Lantian Li
||
* Attend IS2017.
||
* Go on speaker segmentation tasks.
|-

|-
|Zhiyuan Tang
||
* several indicators for VV scoring system, see [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a1/VV_scoring.pdf].
||
* more indicators, a demo with Shuai.
* toolbook writing.
|-

|}

@@ 第68行： / 第68行： @@
 |Lantian Li
 ||
+* Go on speaker segmentation tasks, see [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=615 here]
 ||
+* Phonetic-aware speaker segmentation.
 |-

@@ 第18行： / 第18行： @@
 |Xiaofei Kang
 ||
+* cutting audio and marking：21 speakers，a total of 1050 sentences
 ||
+* improve the human Test website
 |-

@@ 第9行： / 第9行： @@
 *Finished the phonetic i-vector experiment.
 ||
 *combine PTN and phonetic i-vector.
 |-

@@ 第28行： / 第28行： @@
 ||
 * Perform human test on 21-style speech(add the disguise)
-* Draw t-SNE plots compared with experiment results
+* Draw spectrums and t-SNE plots compared with experiment results
 |-

@@ 第45行： / 第45行： @@
 ||
 * multi decodeing ASR model
-* multi decodeing with fake Lid
+* multi decodeing with fake Lid [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=627 here]
 * read code about TTS
 ||

@@ 第44行： / 第44行： @@
 |Ying Shi
 ||
+* multi decodeing ASR model
 ||
+* employ group softmax to train multi decoding ASR model
 |-

@@ 第25行： / 第25行： @@
 |Miao Zhang
 ||
+* Absent
 ||
+* Perform human test on 21-style speech(add the disguise)
 |-

@@ 第2行： / 第2行： @@
 !Date!!People !! Last Week !! This Week
 |-
-| rowspan="9"|2017.8.21
+| rowspan="9"|2017.9.4
@@ 第16行： / 第16行： @@
 |Xiaofei Kang
 ||
-* Recording new audios from 38 person, located in /work7/tanghui/kangxf/workspaces/speaker/wavdata/V2.0
-* Improve the test website to judge before committing
 ||
-* Test the new recording。
 |-
@@ 第35行： / 第34行： @@
 |Yanqing Wang
 ||
-* pruning the connections and refining, [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=626 results]
+* Absent.
 ||
-* Absent.
 |-
@@ 第44行： / 第43行： @@
 |Ying Shi
 ||
-* check toolkit code
-* multilingual baseline system
 ||
-* train language id model
-* use Lid to do multi-decoding
-* some experiments for zhiyong zhang about TTS
 |-
@@ 第56行： / 第52行： @@
 |Yixiang Chen
 ||
+* Absent.
 ||
+*
@@ 第65行： / 第61行： @@
 |Lantian Li
 ||
-* Attend IS2017.
 ||
-* Go on speaker segmentation tasks.
 |-
@@ 第74行： / 第70行： @@
 |Zhiyuan Tang
 ||
-* several indicators for VV scoring system, see [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a1/VV_scoring.pdf].
+* more indicators for VV scoring system, see [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a1/VV_scoring.pdf].
 ||
 * more indicators, a demo with Shuai.