语音通信中,区别发音段和非发音段具有一定的意义,其关键在于提取发音段和非发音段的不同特征参数。本文基于混沌信号处理,提出了一种新的语音、噪声判别方法。该方法提取信号在不同相空间重构维下的虚邻点,从而根据信号高维虚邻点平台的不同,判别发音段和非发音段(背景噪声)以及发音段所含噪声的强弱。本文阐述了该方法的原理,讨论了其性能。仿真实验表明,本方法具有较好的结果。%This paper presents a new method to detect voice from backgroundnoise,which is based on the idea of chaos theory.It extracts a characteristic parameter from the signals-embedding dimension.The principle is explained and the algorithm is proposed.Simulation results show that this method has good performance.
展开▼