摘要
语音特征参数是语音信号分析的重要参数依据,藏语语音特征参数的精确度直接影响藏语语音合成、语音识别及语音压缩等处理的效果。介绍了藏语时域语音信号处理过程中的语音特征参数及其提取关键技术:包括短时平均能量,短时平均幅度,短时过零率,短时自相关函数和端点检测等算法.分析了语音的时域特征参数在藏语语音分析中的实际应用。
the Tibetan speech characteristic parameter is one of the most important basis for analyzing Tibetan speech signals. The accuracy of speech characteristic parameter affects the results of speech synthesis, speech recognition and speech compressing.This paper introduces core speech characteristic parameters and key technologies for processing time domain signal of Tibetan speech. These characteristic parameters include short-time average energy, short-time average zero crossing rate, short-time auto-correlative function, end-point detection and so on. It also studied the actual characteristic parameters application in Tibetan speech signal analysis.
出处
《电脑知识与技术》
2018年第3Z期186-188,共3页
Computer Knowledge and Technology
基金
西藏自治区自然科学基金资助项目(XZ2017ZRG-10)
国家自然科学基金资助项目(61461047)
国家自然科学基金资助项目(61561046)
关键词
藏语语音
特征参数
短时平均能量
短时平均过零率
自相关函数
Tibetan speech
characteristic parameter
short-time average energy
short-time average zero crossing rate
autocorrelative function
