一种基于分带谱熵和谱能量的语音端点检测算法  

A Speech Endpoint Detection Algorithm Based on the Band-partitioning Spectral Entropy and Spectral Energy

作　　者：李如玮[1] 鲍长春[1] 

机构地区：[1]北京工业大学 电子信息与控制工程学院,北京100022

出　　处：《北京工业大学学报》2007年第9期920-924,共5页Journal of Beijing University of Technology

基　　金：北京市教委科技发展计划顶目(KM200710005001);北京工业大学研究生科技基金(ykj-2005-018);北京市优秀人才培养资助项目(20061D0501500202).

摘　　要：语音端点检测的精确度直接影响语音识别的准确度.在噪声环境下,语音端点检测很困难.信噪比下降,语音端点检测的正确率也随之下降,同时,噪声类型的变化影响端点检测的正确率.为此,提出了一种改进的、适合在电话语音城市名识别系统中应用的端点检测算法,并结合分带谱熵和谱能量形成了一个新的特征参数集,利用该参数集进行端点检测,弥补了分别采用分带谱熵和谱能量进行端点检测的缺陷,提高了检测性能.The accuracy of speech recognition directly depends on accurate endpoint detection. Endpoint detection is a very difficult task in the noise environment. It will be degraded with the decrease of SNR and different noise affects the accuracy of speech recognition. As a result, this paper proposed an endpoint detection approach which is applicable to the telephone speech recognition system for city＇s name. The approach integrates band-partitioning spectral entropy and spectral energy to form a set of new feature parameters that can compensating the drawback of entropy and energy so that the performance of the detection is improved.

关 键 词：语音处理 语音识别 谱分析 端点检测 分带谱熵 

分 类 号：TN912.3[电子电信—通信与信息系统]