원문정보
피인용수 : 0건 (자료제공 : 네이버학술정보)
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
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
저자정보
참고문헌
자료제공 : 네이버학술정보