基于mel标度频谱和音素分割的汉语语音单词端点检测方法  

A New Approach of Endpoint Detection(Endpoint Detection Based on Mel-Scale Features and Phoneme Segmentation )

作　　者：丁昊[1] 姚天任[1] 

机构地区：[1]华中科技大学电子与信息工程系,武汉430074

出　　处：《计算机与数字工程》2005年第3期57-59,共3页Computer & Digital Engineering

摘　　要：利用语音声学信号的频谱分析来寻找连续语音信号帧的分割点 ,再结合音素分割方法 ,成功的提高了分割精度。实验表明mel标度频谱法比传统的以信号的短时能量 ,过零率等简单特征作为判决特征参数的语音端点检测方法更适合语音的分割。This paper presents our work on endpoint detection based on mel-scale features and phoneme segmentation.The conventional speech detection methods based on some simple features such as energy cannot work as good as mel-scale features.The experiments show that the high accurate detection can be obtained.

关 键 词：音素分割 mel标度频谱法 端点检测 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]