1) Mel Frequency Principal Coefficient (MFPC)
Mel频率主分量参数(MFPC)
2) Mel-Frequency Cepstral Coefficients(MFCC)
Mel频率倒谱参数
3) Mel frequency cepstral coefficient (MFCC)
Mel频标倒谱参数
4) MFCC
Mel频率倒谱系数
1.
In this paper,we first propose an improved Mel-frequency cepstrum coefficients(PL-MFCC) which acquires by substituting logarithm by a new combined function fPL(x) to amend the noisy sensitivity of the logarithm.
通过研究在低能量段用幂函数代替自然对数函数对Mel滤波器组的输出进行处理,从而得到一种改进Mel频率倒谱系数(PL-MFCC)。
2.
In order to make identification from the speech signal,based on analysis of the conventional identical algorithm,it proposes an advanced method,which uses Mel Frequency Ceptral Coefficients(MFCC) as feature parameters.
为实现由语音信号进行说话人身份的辨识,研究了以往的实现说话人辨认的系统,提出一种改进的算法,采用能够反映人对语音感知特性的Mel频率倒谱系数(MFCC)作为特征参数,即基于概率神经网络(PNN)的识别方法。
3.
The MFCC feature of speech is extracted to recognize vowel(a,i,u)through SVM classifier.
以Mel频率倒谱系数(MFCC)作为语音特征,通过SVM分类器进行元音a,i,u的识别,根据其对应量化后的语音能量,映射到嘴形序列,进行中值滤波和排除"奇异点"。
5) Filter-Normalized Mel Frequency Cepstrum Coefficient
滤波规整的Mel频率倒谱参数
1.
In this paper the characteristics of the reverberant speech are discussed and a new robust feature -Filter-Normalized Mel Frequency Cepstrum Coefficient (FNMFCC) is proposed.
通过讨论室内混响声场中语音的特点,提出用鲁棒性特征参数——滤波规整的Mel频率倒谱参数(FNMFCC),即MFCC参数在对数功率谱域进行低通滤波,倒谱域进行均值减,并用标准差加权进行非线性规整,采用这3种措施来消除混响引起的语音参数的变化,识别方法用矢量量化法,用4组无混响数码语音进行训练,对特定人无混响和4种混响声场中共150组数码音的平均识别率达到98。
6) Mel-frequency
Mel频率
1.
On the basis of analyzing the recognition of speech under G-Force by using each Mel-frequency scale,two kinds of modified Mel-frequency scales which can emphasize the effect of the middle frequency ranges are explored in this paper,consequently,the relative MFCCs are selected as the features for recognition of speech under G-Force.
文章在对应力影响下变异语音进行分频带分析的基础上,选用了可以提升语音信号中频段影响的修正Mel频率映射,并将其对应的MFCC系数作为新的语音识别特征。
补充资料：频率计量(见时间频率计量)
频率计量(见时间频率计量)
frequency metrology: see time and frequency metrology
口n IQ liliang顷率频率计皿(f比quency metrolo盯) 计t。见时闰
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条