Speaker identification through use of features selected using genetic algorithm

Date

1998-01-08

Author

Haydar, A
Demirekler, Mübeccel
Yurtseven, MK

Metadata

Show full item record

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

Item Usage Stats

141
views

0
downloads

The authors introduce the use of a genetic algorithm in the reduction of a 24 parameter (12 LPC derived cepstral coefficients +12 Delta-cepstral coefficients) set to a five, six, seven, eight or ten parameter set, for each speaker in text-independent speaker identification. The experimental results show that there is similar to 5% increase in the recognition rate when the reduced set of parameters is used.

Subject Keywords

Electrical and Electronic Engineering

URI

https://hdl.handle.net/11511/56655

Journal

ELECTRONICS LETTERS

DOI

https://doi.org/10.1049/el:19980126

Collections

Graduate School of Natural and Applied Sciences, Article

Suggestions

OpenMETU
Core

HMM topology for boundary refinement in automatic speech segmentation Akdemir, E.; Çiloğlu, Tolga (Institution of Engineering and Technology (IET), 2010-07-22) A boundary refinement method using a new hidden Markov model (HMM) topology is proposed for automatic phonetic speech segmentation. The proposed method has the ability to work at high frame rates and the training and boundary refinement stages are easy and fast. The method is data driven and can be adapted to any speech segmentation problem provided that a training set is available. Given an initial segmentation obtained by forced alignment using an HMM based phone recogniser, 20% decrease in boundary error...
Performance Enhancement of the Single-Phase Series Active Filter by Employing the Load Voltage Waveform Reconstruction and Line Current Sampling Delay Reduction Methods Senturk, Osman S.; Hava, Ahmet Masum (Institute of Electrical and Electronics Engineers (IEEE), 2011-08-01) This paper proposes the waveform reconstruction method (WRM), which is utilized in the single-phase series active filter's (SAF's) control algorithm, in order to extract the load harmonic voltage component of voltage harmonic type single-phase diode rectifier loads. Employing WRM and the line current sampling delay reduction method, a single-phase SAF compensated system provides higher harmonic isolation performance and higher stability margins compared to the system using conventional synchronous-reference...
Multipath Characteristics of Frequency Diverse Arrays Over a Ground Plane Cetintepe, Cagri; Demir, Şimşek (Institute of Electrical and Electronics Engineers (IEEE), 2014-07-01) This paper presents a theoretical framework for an analytical investigation of multipath characteristics of frequency diverse arrays (FDAs), a task which is attempted for the first time in the open literature. In particular, transmitted field expressions are formulated for an FDA over a perfectly conducting ground plane first in a general analytical form, and these expressions are later simplified under reasonable assumptions. Developed formulation is then applied to a uniform, linear, continuous-wave opera...
Implementation of the Equivalence Principle Algorithm for Potential Integral Equations Farshkaran, Ali; Ergül, Özgür Salih (Institute of Electrical and Electronics Engineers (IEEE), 2019-05-01) A novel implementation of the equivalence principle algorithm (EPA) employing potential integral equations (PIEs) is presented. EPA is generalized to be compatible with PIEs that are used to formulate inner problems inside equivalence surfaces. Based on the stability of PIEs, the resulting EPA-PIE implementation is suitable for low-frequency problems involving dense discretizations with respect to wavelength. Along with the formulation and a clear demonstration of the EPA-PIE mechanism, high accuracy, stabi...
Derivation of length extension formulas for complementary sets of sequences using orthogonal filterbanks Candan, Çağatay (Institution of Engineering and Technology (IET), 2006-11-23) A method for the construction of complementary sets of sequences using polyphase representation of orthogonal filterbanks is presented. It is shown that the case of two-channel filterbanks unifies individually derived length extension formulas for complementary sequences into a common framework and the general M-channel case produces novel formulas for the extension of complementary sets of sequences. The presented technique can also be used to generate polyphase and multilevel sequences.

Citation Formats

A. Haydar, M. Demirekler, and M. Yurtseven, “Speaker identification through use of features selected using genetic algorithm,” ELECTRONICS LETTERS, pp. 39–40, 1998, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/56655.