MFCC speech feature extraction process of the MFCC
2016-08-23
0 0 0
no vote
Other
Earn points
Application background
In speech recognition, speech recognition and speaker recognition (speaker recognition) aspects, the most commonly used speech feature is Mel frequency cepstrum coefficient (Mel-scale frequency cepstral coefficients, referred to as the MFCC). According to the study of the mechanism of ear hearing, the human ear has different hearing sensitivity to different frequency of sound waves.. Speech signals from 5000Hz to 200Hz are affected by the intelligibility of speech.. Two different loudness of sound in the ear, loudness high frequency components will affect the feelings of loudness lower frequency components, so that it becomes difficult to detect, this phenomenon is known as the masking effect. Due to the low frequency sound in the cochlear basilar membrane traveling wave transmission distance is greater than the higher frequency sound. Therefore, in general, bass tend to mask the treble and bass treble masking is difficult. The critical bandwic
语音
mfcc
提取
参数
过程
详解
特征
Related Source Codes
PClite
0
0
no vote
generic embeded FTP Client
0
0
no vote
UDP Test Demo
0
0
no vote
TMS320F28335 DSP transmits data to EEPROM through
0
0
no vote
TMS320F28335 CAN communication source code
0
0
no vote
No comment