Asr-project-segment - 版本历史

2017年11月30日 (四) 11:56 Cslt

2017-11-30T11:56:39Z

Cslt：/* Demonstration */

2017-11-16T05:04:59Z

‎Demonstration

Cslt：/* Demonstration */

2017-11-16T05:04:35Z

‎Demonstration

Cslt：以“==Introduction== Speaker segmentation is important for many applications, among which include speaker-dependent adaptation, telephone archive analysis. Traditional...”为内容创建页面

2017-11-16T05:03:42Z

以“==Introduction== Speaker segmentation is important for many applications, among which include speaker-dependent adaptation, telephone archive analysis. Traditional...”为内容创建页面

新页面

==Introduction==

Speaker segmentation is important for many applications, among which include speaker-dependent adaptation, telephone archive analysis. Traditional approaches
include ergodic HMM re-estimation, turn point detection and clustering, i-vector clustering. All these methods, however, are highly vulnerable for noise corruptions,
speech overlapping, data imbalance.

We developed a deep segmentation approach that is based on deep learning approach that can analysis the true underlying speaker properties of speech signals, and then
use simple clustering methods to achieve very high accuracy in segmentation.

==Demonstration==

A demo can be found <http://47.92.96.222/display/demo/?button=Call1_18_44741326_1_26 here>

<img src=http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/22/Seg.png>

@@ 第10行： / 第10行： @@
 ==Demonstration==
-A demo can be found [http://47.92.96.222/display/demo/?button=Call1_18_44741326_1_26 here]
 [[文件:Seg.png]]

←上一版本		2017年11月16日 (四) 05:04的版本
第12行：		第12行：
	A demo can be found [http://47.92.96.222/display/demo/?button=Call1_18_44741326_1_26 here]		A demo can be found [http://47.92.96.222/display/demo/?button=Call1_18_44741326_1_26 here]

−	[~~媒体文件~~:Seg.png]	+	[[文件:Seg.png]]