Speaker Recognition Based on i-vector and Improved Local Preserving Projection

Di Wu, Jie Cao, HuaJin Wang


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


Computer Application;i-vector; Local Preserving Projection;Manifold Learning; Speaker Recognition

Full Text:

Total views : 57 times


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

shopify stats IJEECS visitor statistics