search

jameslyons / python_speech_features

This library provides common speech features for ASR including MFCCs and filterbank energies.
MIT License
2.38k stars 617 forks source link

39 dimensional MFCC #53

Closed dmoham1476 closed 7 years ago

dmoham1476 commented 7 years ago

I generated 13 MFCC co-efficents using mfcc().

mfcc_feat = mfcc(audio_data, sample_rate, winlen=0.025, winstep=0.01, numcep=13, nfilt=26, nfft=512, lowfreq=0, highfreq=None, preemph=0.97, ceplifter=22, appendEnergy=True)

How can I get delta and delta-delta cepstrum so I can build a 39 dimensional MFCC? Deepa

jameslyons commented 7 years ago

mfcc_feat = mfcc(sig,rate) d_mfcc_feat = delta(mfcc_feat, 2) a_mfcc_feat = delta(d_mfcc_feat, 2)

feat = np.hstack([mfcc_feat, d_mfcc_feat, a_mfcc_feat])

feat should be n by 39 dimensional matrix

dmoham1476 commented 7 years ago

Thanks a lot!

On Mon, Nov 6, 2017 at 4:40 PM, James Lyons notifications@github.com wrote:

mfcc_feat = mfcc(sig,rate) d_mfcc_feat = delta(mfcc_feat, 2) a_mfcc_feat = delta(d_mfcc_feat, 2)

feat = np.hstack([mfcc_feat, d_mfcc_feat, a_mfcc_feat])

feat should be n by 39 dimensional matrix

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/jameslyons/python_speech_features/issues/53#issuecomment-342336588, or mute the thread https://github.com/notifications/unsubscribe-auth/ANhyLRLfI5ZJoZwdML4tObQex1Ryb1bvks5sz6b6gaJpZM4QT7Q5 .