基于对数包络的汉语音节切分算法  

Chinese Syllable Segmentation Algorithm with Logarithmic Envelope

作　　者：唐维康 邵玉斌[1] 龙华[1] Tang Weikang;Shao Yubin;Long Hua(School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,Yunnan,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《激光与光电子学进展》2022年第10期54-61,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61761025)。

摘　　要：为提升目前连续汉语音节切分算法在噪声环境中的切分效果,基于汉语语音的对数包络特征提出一种音节切分算法,用曲线插值法获取信号包络,再经滤波和对数运算获取对数时域包络,然后采用门限判决从包络上获取极值点,根据极值点的分布特性确定音节的切分边界。所提方法对无噪汉语语音的音节切分效果优于传统方法,且在低信噪比情况下仍具有较高的切分准确率。A syllable segmentation algorithm with the logarithmic envelope feature of Chinese speech is proposed to improve the segmentation effect of existing continuous Chinese syllable segmentation algorithms in noisy environment. The voice envelope is obtained by curve interpolation, and then the logarithmic time-domain envelope is obtained by filtering and logarithmic operation. Extreme points are obtained with the threshold judgment. Finally,the syllable segmentation boundary is determined according to the distribution of extreme points. The proposed algorithm is more effective than traditional ones for syllable segmentation of Chinese speech without noises, and still has a high segmentation accuracy at low signal-to-noise ratio.

关 键 词：信号处理 音节切分 对数包络 极值点 语音包络 

分 类 号：TN912.34[电子电信—通信与信息系统]