Leian Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Leian Liu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Ying Zou
2 shared publicationsJichen Yang
School of Information Science and Technology Zhongkai University of Agriculture and Engineering Guangzhou People's Republic of China
1 shared publication- Ling Yang
College of Automation, Zhongkai University of Agriculture and Engineering, Guangzhou, China
1 shared publication Qianhua He
School of Electronic and Information Engineering South China University of Technology Guangzhou People's Republic of China
1 shared publication- Yu-Qiang Shi
College of Information Science and Technology Zhongkai University of Agriculture and Engineering Guangzhou China
1 shared publication
Latest Publications
- Open Access
- 1 July 2019
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 55 (15) , 861-864
Discriminative feature based on FWMW for playback speech detection
A discriminative feature extraction method for playback speech detection is proposed, it relies on the finding that frame‐wise magnitude‐spectrum weight (FWMW) can enlarge the difference between genuine speech and playback speech. The proposed FWMW is obtained by supplying the sum of every frame magnitude spectrum frequency bin as the weight on the frame magnitude spectrum. Then, a new feature based on FWMW is proposed, namely constant‐Q weight segmentation coefficients (CQWSCs). The experimental result on ASVspoof 2017 version 2.0 evaluation set using CQWSC indicates that: (i) FWMW can make the proposed feature has more discriminative ability and the equal error rate can decline 15.53 and 19.18% under Gaussian mixture model and deep neural network, respectively, and (ii) CQWSC performs better than some commonly used features.
- 1 July 2019
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 55 (15) , 861-864
Open AccessDiscriminative feature based on FWMW for playback speech detection
A discriminative feature extraction method for playback speech detection is proposed, it relies on the finding that frame‐wise magnitude‐spectrum weight (FWMW) can enlarge the difference between genuine speech and playback speech. The proposed FWMW is obtained by supplying the sum of every frame magnitude spectrum frequency bin as the weight on the frame magnitude spectrum. Then, a new feature based on FWMW is proposed, namely constant‐Q weight segmentation coefficients (CQWSCs). The experimental result on ASVspoof 2017 version 2.0 evaluation set using CQWSC indicates that: (i) FWMW can make the proposed feature has more discriminative ability and the equal error rate can decline 15.53 and 19.18% under Gaussian mixture model and deep neural network, respectively, and (ii) CQWSC performs better than some commonly used features.
- 1 January 2019
- Published by EJournal Publishing in International Journal of Information and Education Technology
- Vol. 9 (6) , 396-401
Exploration and Practice on Training Mode of Innovative Network Engineering Talents
- 1 January 2019
- Published by EJournal Publishing in International Journal of Information and Education Technology
- Vol. 9 (6) , 396-401
Exploration and Practice on Training Mode of Innovative Network Engineering Talents
- Open Access
- 1 January 2018
- Published by Clausius Scientific Press, Inc. in Advances in Educational Technology and Psychology
- Vol. 2 (1) , 220-227
Teaching Reform of Computer Network Course for Engineering Applications
This paper takes application-oriented undergraduate colleges and universities as the target, and aims at cultivating students’ engineering application ability. It analyzes the main problems existing in computer network teaching at present and summarizes some reforms and achievements of ours in the aspects of the theoretical teaching content, teaching team building, construction of online course resources, application of teaching aids, and practical teaching content, etc. The reforms of this paper provide some reference for the reform of computer network courses in similar colleges and universities.
- 1 January 2018
- Published by Clausius Scientific Press, Inc. in Advances in Educational Technology and Psychology
- Vol. 2 (1) , 220-227
Open AccessTeaching Reform of Computer Network Course for Engineering Applications
This paper takes application-oriented undergraduate colleges and universities as the target, and aims at cultivating students’ engineering application ability. It analyzes the main problems existing in computer network teaching at present and summarizes some reforms and achievements of ours in the aspects of the theoretical teaching content, teaching team building, construction of online course resources, application of teaching aids, and practical teaching content, etc. The reforms of this paper provide some reference for the reform of computer network courses in similar colleges and universities.