“ASR Status Report 2017-7-3”版本间的差异

2017年7月10日 (一) 05:20的最后版本

Date	People	Last Week	This Week
2017.7.3	Miao Zhang	prepared for the report did translation	do a report finish the website comfirm the next work direction with Tanghui and yixiang
	Hui Tang	submitted the technical report finished to check the subset(happy) of our speech database test the model of detecting overlapped speech results	check the subset(angry) of our database finish the website with zhangmiao and yixiang
	Yanqing Wang	use dnn & sigmoid to prune result	Importance of each layer; try Tanh.
	Ying Shi	kazak ASR transfor learning help zheling Zhang to learn Scrapy	finish kazak ASR　transfor learning help zheling Zhang to write his first Web crawler
	Yixiang Chen	absent.
	Lantian Li	write book. check the process of deep speaker segmentation. demo for speech synthesis.	deep speaker visulization and segmentation.
	Zhiyuan Tang	Compile auto-scoring system; Chinglish for mix-asr training.	A report about the research of the speech group (Thursday); Into the source code of auto-scoring system;

Date	People	Last Week	This Week
2017.6.26	Miao Zhang	check the paper	build up an experimental website
	Hui Tang	write the technical report of overlapped speech help jiayu do speaker diarization .	check a speech database write the technical report
	Yanqing Wang	absent.	try rectifier activation function in experiments.
	Ying Shi	finish the paper about kazak speech recognition back to home	transfor learning about kazak speech recognition
	Yixiang Chen	absent.
	Lantian Li	finish the papers for APSIPA 2017. prepare the deepspk for TASLP.	finish the deepspk for TASLP.
	Zhiyuan Tang	test auto-scoring system.	update auto-scoring system.

@@ 第12行： / 第12行： @@
 * do a report
 * finish the website
+* comfirm the next work direction with Tanghui and yixiang
 |-
@@ 第18行： / 第19行： @@
 ||
 * submitted the technical report
+* finished to check the subset(happy) of our speech database
 * test the model of detecting overlapped speech
-{|class="wikitable"
+[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tanghui&step=view_request&cvssid=610 results]
-|dataset||FER of original speech ||FER of overlapped speech|| total
-|-
-|th30||19.4%||15.3%|| 17.3%
-|-
-|dataset||FER of original speech||FER of overlapped speech of same words|| FER of overlapped speech of diff words
-|-
-|real environment||19.4%||28%|| 37.8%
-|
-|-
-|}
 ||
-*
+* check the subset(angry) of our database
+* finish the website with zhangmiao and yixiang
 |-
@@ 第38行： / 第31行： @@
 |Yanqing Wang
 ||
-*
+* use dnn & sigmoid to prune [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/4e/Dnn_sigmoid.pdf result]
 ||
-*
+* Importance of each layer; try Tanh.
 |-
@@ 第47行： / 第40行： @@
 |Ying Shi
 ||
-*
+* kazak ASR transfor learning
+* help zheling Zhang to learn Scrapy
 ||
-*
+* finish kazak ASR　transfor learning
+* help zheling Zhang to write his first Web crawler
 |-
@@ 第65行： / 第60行： @@
 |Lantian Li
 ||
-*
+* write book.
+* check the process of deep speaker segmentation.
+* demo for speech synthesis.
 ||
-*
+* deep speaker visulization and segmentation.
 |-