“News-2018-01-30”版本间的差异
（以“'''<b>Lantian Li, Dong Wang, Yixiang Chen, Ying Shi, Zhiyuan Tang, "DEEP FACTORIZATION FOR SPEECH SIGNAL"''' This paper describes how speech signals can be factoriz...”为内容创建页面） |
|||
| （相同用户的一个中间修订版本未显示） | |||
| 第1行： | 第1行： | ||
| − | ''' | + | We have three papers aceepted by ICASSP 2018. Congratulations to the authors! |
| + | |||
| + | 1. '''Lantian Li, Dong Wang, Yixiang Chen, Ying Shi, Zhiyuan Tang, "DEEP FACTORIZATION FOR SPEECH SIGNAL"''' | ||
This paper describes how speech signals can be factorized into varios informative factors in the latent | This paper describes how speech signals can be factorized into varios informative factors in the latent | ||
| 第6行： | 第8行： | ||
More information about this research can be found in the [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Deep_Speech_Factorization project page] | More information about this research can be found in the [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Deep_Speech_Factorization project page] | ||
| − | '''Lantian Li, Zhiyuan Tang, Dong Wang, "FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING"''' | + | 2. '''Lantian Li, Zhiyuan Tang, Dong Wang, "FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING"''' |
It presents a new idea to learn 'pure features', by pushing all the discriminative information to | It presents a new idea to learn 'pure features', by pushing all the discriminative information to | ||
| 第13行： | 第15行： | ||
More information about this research can be found in the [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Deep_Speaker_Feature_Learning project page] | More information about this research can be found in the [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Deep_Speaker_Feature_Learning project page] | ||
| + | 3. '''Miao Zhang, Xiaofei Kang, Yanqing Wang, Lantian Li, Zhiyuan Tang, Haisheng Dai, Dong Wang, "HUMAN AND MACHINE SPEAKER RECOGNITION BASED ON SHORT TRIVIAL EVENTS"''' | ||
| − | + | It presents how machines can discriminate speakers by trivial events such as laugh, cough, en. | |
| − | + | ||
| − | It presents how machines can discriminate speakers by trivial events such as laugh, cough, en. | + | |
More information about this research can be found in the [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Speaker_Recognition_on_Trivial_events project page]. | More information about this research can be found in the [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Speaker_Recognition_on_Trivial_events project page]. | ||
2018年1月29日 (一) 23:14的最后版本
We have three papers aceepted by ICASSP 2018. Congratulations to the authors!
1. Lantian Li, Dong Wang, Yixiang Chen, Ying Shi, Zhiyuan Tang, "DEEP FACTORIZATION FOR SPEECH SIGNAL"
This paper describes how speech signals can be factorized into varios informative factors in the latent space.
More information about this research can be found in the project page
2. Lantian Li, Zhiyuan Tang, Dong Wang, "FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING"
It presents a new idea to learn 'pure features', by pushing all the discriminative information to feature learning. It provides stonger features than regular feature + softmax regression architecture.
More information about this research can be found in the project page
3. Miao Zhang, Xiaofei Kang, Yanqing Wang, Lantian Li, Zhiyuan Tang, Haisheng Dai, Dong Wang, "HUMAN AND MACHINE SPEAKER RECOGNITION BASED ON SHORT TRIVIAL EVENTS"
It presents how machines can discriminate speakers by trivial events such as laugh, cough, en.
More information about this research can be found in the project page.
