Earticle

초록

영어

In this paper, a general voice activity detection (VAD) method based on pattern recognition is proposed, and a specific algorithm of endpoint detection is researched. In this method, the Extreme Learning Machine (ELM) and Genetic Algorithm (GA) optimization Support Vector Machine (SVM) is used as the training and recognition model. The simulation results indicates that ELM and GA-SVM have the same superior endpoint detection accuracy, and recognition time were similar, but the training time of ELM only up to a 1/2000 of the GA-SVM, the robustness of ELM and GA-SVM is greatly improved in noisy environment compare with the traditional VAD that depends on time-domain energy and zero crossing rate.

목차

Abstract
 1. Introduction
 2. The Theory of Endpoint Detection
 3 Algorithm of VAD
  3.1. Feature Selection
  3.2. Determination of Preprocessing Parameters and Extraction Feature Order
  3.3. Endpoint Detection Algorithm
  3.4. Introduction of ELM Algorithm
  3.5. Introduction of Support Vector Machines
  3.6. The Rescreen of Detection Results
 4. Endpoint Detection Algorithm Performance Evaluations
  4.1. The Training of SVM
  4.2 The Training of ELM
  4.3 The Comparison of Endpoint Detection Effectiveness
 5. Conclusions
 References

키워드

저자

• Zhigang Feng [ School of Automation, Shenyang Aerospace University, Shenyang, Liaoning, China ]
• Junlei Feng [ School of Automation, Shenyang Aerospace University, Shenyang, Liaoning, China ]
• Fangyuan Dai [ School of Automation, Shenyang Aerospace University, Shenyang, Liaoning, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Control and Automation

• 간기

  월간

• pISSN

  2005-4297

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605