根据群延迟函数与倒谱系数之间的关系,可以确定分母的多项式系数。
Based on the relationship between the group delay function and the cepstral coefficients, the denominator polynomial coefficients can be determined.
实验中,采用美尔倒谱系数(MFCC)作为话者语音特征参数。
During the experiment, MFCC (Mel Frequency Ceptral Coefficient) is adopted to speaker speech feature parameters.
实验证明这种混合倒谱系数具有较好的分类特性、抗噪性和稳定性。
The results of comparison prove that CDCC is better in classification, noise restraint and stability that LPCC.
提出一种基于复倒谱系数均值比较的数字音频健壮、透明及盲水印算法。
This paper proposed a robust, transparent and blind digital audio watermarking algorithm base on complex cepstrum coefficient mean comparison.
选用美尔倒谱系数及其差分作为语音识别的特征参数,来描述人耳的听觉频率非线性特性。
Selected for use MFCC and the difference and divided the characteristic parameter as phonetic recognition, to describe the non-linear characteristic of frequency of sense of hearing of ears of people.
系统提取的音频信号特征为线性预测美尔倒谱系数(LPCMCC),采用动态时间规整(DTW)的识别算法。
The audio signal feature, in this scheme, is the LPC Mel Cepstrum Coefficient (LPCMCC) and recognition algorithm is Dynamic Time Warping (DTW).
本文应用全极点模型,提取语音信号的线性预测系数,并推导出其倒谱系数,获得线性预测倒谱差分,用以描述说话人声道的动态变化。
In this paper, we use full pole model to obtain speech signal LPC, then deduce it's LPCC, and we use the LPCC difference to describe speaker's track dynamic movement.
通过应用全极点模型,提取语音信号的线性预测系数,并推导出其倒谱系数,获得线性预测倒谱差分,用以描述说话人声道的动态变化。
By using full pole model, we obtained speech signal LPC, then deduced it's LPCC, and we used the LPCC difference to describe speaker's track dynamic movement.
该方法是基于最小相位滤波器的复倒谱系数和其群迟延函数以及其系统函数之间的关系,通过一个非线性的递归方程求解分母多项式的系数。
Based on the relationship between the group delay function and the cepstral coefficients, the denominator polynomial coefficients can be determined through a nonlinear recursive difference equation.
文章在分析数字音频水印同步性的基础上提出了一种结合音频倒频谱系数和以音频能量特征决定数字水印嵌入位置的数字水印方法。
This paper gives a new method for digital audio watermarking which uses audio cepstrum domain and energy features to decide the location of embed frames.
文章在分析数字音频水印同步性的基础上提出了一种结合音频倒频谱系数和以音频能量特征决定数字水印嵌入位置的数字水印方法。
This paper gives a new method for digital audio watermarking which uses audio cepstrum domain and energy features to decide the location of embed frames.
应用推荐