FreeNeb Status Report 2017-12-25 - 版本历史

2017年12月25日 (一) 03:09 Zhaomy

2017-12-25T03:09:02Z

2017年12月25日 (一) 02:03 Zhaomy

2017-12-25T02:03:29Z

2017年12月25日 (一) 01:51 Zhangshuai

2017-12-25T01:51:46Z

2017年12月25日 (一) 01:44 Zhaomy

2017-12-25T01:44:02Z

2017年12月25日 (一) 01:42 Zhangzy

2017-12-25T01:42:42Z

2017年12月25日 (一) 01:36 Jinyanchi

2017-12-25T01:36:42Z

2017年12月25日 (一) 01:00 Zhaomy

2017-12-25T01:00:09Z

Zhaomy：以“This Week: {| class="wikitable" !People !! Last Week !! This Week !! Meet Minutes !! Task Tracing(DeadLine) |- |Mengyuan Zhao || * Engineeri...”为内容创建页面

2017-12-25T00:56:53Z

以“This Week: {| class="wikitable" !People !! Last Week !! This Week !! Meet Minutes !! Task Tracing(<font color="red">DeadLine</font>) |- |Mengyuan Zhao || * Engineeri...”为内容创建页面

新页面

This Week:
{| class="wikitable"
!People !! Last Week !! This Week !! Meet Minutes !! Task Tracing(<font color="red">DeadLine</font>)
|-
|Mengyuan Zhao ||
* Engineering
# Optimize TTS-pyserver to speed up.
# Working on online-ASR DEMO.
||
* Engineering
# Try to finish first version of online-ASR APP.
# Clean up code and draft documents.
||
* Roobo
# Prepare a workshop(half a day) in Jan 2018 after Jan.20,2018.
* Engineering
# Improve speed of TTS engine
# Draft documents for many engines: fnasr, fntts, deepfe....
||

|-
|Zhiyong Zhang ||
* Finished 100h 16k TTS training
:* Poor synthesised wavs, the reason may be
::* Noise corrupted wav may not fit TTS task, the corrupted spectrum would be learned too;
::* I assumed one utterence for one specified person, not so accurate, may another reason?

||
* To train duration-model using 16k data.

||
* Aiweier
# Contact with Aiweier.
* Myhexin
# Draft a document and contact with Myhexin.
||

|-
|Yang Wei ||
* Write test specification for FreeNeb TTS pyserver.
* Test pyserver.
||
* Add new cases to test FreeNeb TTS pyserver.
||
* Continue test TTS pyserver
||

|-
|Dong Wang||
* Some discussion with Fenyinta
* Some discussion with Japan Tongfang
* More people will join!
||
* APSIPA 2017
||

||

|-
|Zhenlong Han||
* write document.
* train some model with 8k and 16k, and add ivector to it.
||
* English embedded model training.
||
* Prepare all the ASR models:
||

|-
|Shuai Zhang||
* Add the function of asking.
* Add the edit-distance algorithm.
* fixed the bugs in answering the question.
||
* Test the Megrez project overall.
* Complete the VVParrot project.
* Add the documents about the two project.
||

||
* the test by ourselves about the Megrez will be done 20th Dec.
* the VVParrot will be finished the standard function 28th Dec which will include login, register, record the score and get the sentence randomly.

|-
|Yanchi Jin||
* Already update the version of Megrez project and the database.
||
* Complete the Megrez_tool and the chart of structure.
* Continue update the database.
||

||
|-
|}

@@ 第68行： / 第68行： @@
 embedded_6X400X800_tl_xent	       13.49	          8.05	        10.9	         12.83	        32.82
 embedded_6X400X800_tl_xent_kt	       13.71	          8.12	        11.44	         12.92	        31.86
-cloud_6X1200X8000_tl_xent_kt_700mdl                       6.42	        8.63	         11.59
+cloud_6X1200X8000_tl_xent_kt_700mdl    10.78              6.42	        8.63	         11.59	        27.29
 ||
@@ 第84行： / 第84行： @@
 * Modify the edit-distance algorithm.
 ||
+# graph to json toolkit v0.1 release. Dec.27.
 ||
 * the test by ourselves about the Megrez will be done 20th Dec.

@@ 第63行： / 第63行： @@
 |-
 |Zhenlong Han||
-* write document.
+* English embedded model finish, and cloud model have training 700 model
-* train some model with 8k and 16k, and add ivector to it.
+	                               libri_clean	wsj_eval92	wsj_eval93	voxforge	libri_other
 ||
 * English embedded model training.

@@ 第73行： / 第73行： @@
 |-
 |Shuai Zhang||
-* Add the function of asking.
+* Test the Megrez project overall
-* Add the edit-distance algorithm.
 * fixed the bugs in answering the question.
 ||
 * Complete the VVParrot project.
-* Add the documents about the two project.
+* Modify the edit-distance algorithm.
 ||

@@ 第41行： / 第41行： @@
 |-
 |Yang Wei ||
-* Write test specification for FreeNeb TTS pyserver.
+* Locate a failed case
-* Test pyserver.
+* Test the cases that client close incidentally.
 ||
-* Add new cases to test FreeNeb TTS pyserver.
+* Test the cases that network is not stable.
 ||
 * Continue test TTS pyserver

@@ 第22行： / 第22行： @@
 |-
 |Zhiyong Zhang ||
-* Finished 100h 16k TTS training
+* Retrain 100h 16k TTS training
-:* Poor synthesised wavs, the reason may be
+:* The synthesised waves still not seems well, hold
-::* Noise corrupted wav may not fit TTS task, the corrupted spectrum would be learned too;
+* Contact with THS about exist technical problems, still not receive feedback
-::* I assumed one utterence for one specified person, not so accurate, may another reason?
+:* I have finished part of the technical solution
 ||
-* To train duration-model using 16k data.
 ||
 * Aiweier
-# Contact with Aiweier.
+# Contact with Aiweier. --Done
 * Myhexin
 # Draft a document and contact with Myhexin.

@@ 第86行： / 第86行： @@
 |-
 |Yanchi Jin||
-* Already update the version of Megrez project and the database.
+* Already update the database.
 ||
 * Complete the Megrez_tool and the chart of structure.

@@ 第18行： / 第18行： @@
 # Draft documents for many engines: fnasr, fntts, deepfe....
 ||
+# Online-TTS DEMO (<font color="red">Jan.20,2018</font>)
 |-
 |Zhiyong Zhang ||