170712 python_speech_features

Welcome to python_speech_features’s documentation!
Audio tools for Linux commandline geeks
Managing Linguistic Data
Timit
快速克隆网站(Teleport Ultra)

Code:

from python_speech_features import mfccfrom python_speech_features import logfbankimport scipy.io.wavfile as wav(rate,sig) = wav.read("file.wav")mfcc_feat = mfcc(sig,rate)fbank_feat = logfbank(sig,rate)print(fbank_feat[1:3,:])

mfcc_feat, fbank_feat are 2D matrics
mfcc_feat: the number of row stands for the the frame number, each frame(帧) covers a sub-band of signal
mfcc_feat: the number of columns stands for the filters numbers