Jie Cao
Lanzhou University of Technology

Published : 4 Documents
Articles

Found 4 Documents
Search

SPEAKER RECOGNITION BASED ON I-VECTOR AND IMPROVED LOCAL PRESERVING PROJECTION Wu, Di; Cao, Jie; Wang, HuaJin
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 6: June 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In order to enhance the recognition performance of the i-vector speaker recognition system under unpredicted noise environment, a improved local preserve projection which used for reduce dimension to i-vector is proposed on this paper. First , the non zero eigenvalue is rejected when we solve the optimized objective function, only using the eigenvalue which value greater than zero. A mapping matrix is obtained by solving a generalized eigenvalue problem, so can settle the singular value problem occurred in traditional local preserve projection algorithm.The experiment result shows,The recognition performance of the method proposed in this paper is improved under several kinds of noise environments. DOI : http://dx.doi.org/10.11591/telkomnika.v12i6.3994
MODEL REFERENCE ADAPTIVE CONTROL BASED ON LYAPUNOV STABILITY THEORY TANG, Minan; WANG, Xiaoming; CAO, Jie; LI, Ying
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 3: March 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

According to the obvious characteristics of time-varying nonlinear controlled object, in order to improve the control performance, can use appropriate adaptive control strategy. Based on the research object system of a certain amount of input to control variables, according to Lyapunov stability theory, the research object system input/output variable a model reference adaptive control system was design. And after analysis the method to improve the system starting stage characteristics, dynamic process performance and system anti-interference and resistance to process parameters is presented. Simulation and research results show that the proposed control method is effective DOI : http://dx.doi.org/10.11591/telkomnika.v12i3.4450
THE RESEARCH OF DV-HOP POSITIONING ALGORITHM BASED ON RSSI CALIBRATION Cao, Jie; Chen, Mu
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 10: October 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i10.pp7452-7458

Abstract

Because of the DV-HOP algorithm in wireless sensor network (WSN), the first jump range error, which affect the positioning error of the whole node network problems. This paper puts forward an improved algorithm is proposed. The algorithm is mainly using the RSSI ranging technology, in the process of DV-HOP first jump range through correction of RSSI ranging technology, to reduce the distance measuring error, in order to improve positioning accuracy. The simulation results show that compared with traditional DV - HOP algorithm. The improved algorithm can without additional hardware and computation under the premise of improving positioning accuracy.
ACOUSTIC SOURCE LOCALIZATION BASED ON ITERATIVE UNSCENTED PARTICLE FILTER cao, Jie; Liu, Jia-qi; Wu, Di; Wang, Jin-hua
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 5: May 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

To solve the problem of tracking an acoustic source in noise and reverberation environment, a new method is proposed in pursuit of higher accuracy. First, this paper improves the unscented particle filter, which can add the latest measurement information to optimize the proposal distribution. Then, the likelihood function is constructed by calculating the microphone arrays? output energy in the framework of the improved algorithm. Finally, the experiment results indicate that the proposed localization method can not only improves the accuracy of location estimation, but also can enhance the ability to resist noise and reverberation in the acoustic source localization system. DOI : http://dx.doi.org/10.11591/telkomnika.v12i5.4816