本文采用语音信号的正弦表示方法并利用耳蜗模型提取了语音信号的基本特征参数,建立了一个语音分析/合成系统。
The sinusoidal representation of speech signal and a cochlear model are used to extract speech parameters in this paper, and a speech analysis/synthesis system is developed using the model.
基于语音正弦模型,采用能量谱熵和子谐波谐波比率方法进行语音分析。
Energy-spectrum entropy and subharmonic-harmonic rate methods were used to analyze speech based on speech sinusoidal model.
介绍了语音变换的相关技术,分析了利用正弦谐波模型实现语音变换的算法及流程。
The technology of voice transformation was introduced. The algorithm of voice transformation based on harmonic sinusoidal modal was analyzed.
正弦波模型已被证明是一种行之有效的语音信号编码技术。
Sinusoid modeling has proven to be an efficient technique in speech coding.
本文根据语音可以表示为有限项正弦级数的理论,在把耳蜗流体视为实际的粘性流体的条件下,建立了一种新的听觉模型,并在频域上求出了模型的传输函数。
According to the theory that speech can be represented as a sum of sinusoidal waves, a new auditory model is developed on condition that cochlear fluid is considered as actual viscous fluid.
本文根据语音可以表示为有限项正弦级数的理论,在把耳蜗流体视为实际的粘性流体的条件下,建立了一种新的听觉模型,并在频域上求出了模型的传输函数。
According to the theory that speech can be represented as a sum of sinusoidal waves, a new auditory model is developed on condition that cochlear fluid is considered as actual viscous fluid.
应用推荐