CAJ | 학술논문

语音识别中的端点检测技术是语音识别的基础,低信噪比环境下的端点检测很大程度决定语音识别工作的有效进行.提出了一种利用一阶有限差分商结合折半查找来判定语音端点检测的方法,提高了端点检测的准确率.仿真实验表明,在噪声环境下该方法较好地实现了语音端点检测.
어음식별중적단점검측기술시어음식별적기출,저신조비배경하적단점검측흔대정도결정어음식별공작적유효진행.제출료일충이용일계유한차분상결합절반사조래판정어음단점검측적방법,제고료단점검측적준학솔.방진실험표명,재조성배경하해방법교호지실현료어음단점검측.
Endpoint detection of speech recognition technology is the basis of voice recognition,endpoint detection with low SNR environment determined largely the work of speech recognition can be conducted effectively.This paper presents a method based on first-order finite differential quotient with a binary search to determine the endpoint detection;it improves the accuracy of endpoint detection.The emulate experiments show the proposed method can achieve better voice activity detection in a noisy environment.