Please use the code in speech_utils.py and feature_extractor.py. The rest files are used when I developed this project.
All implemented feature extractors have been written in the file ‘feature_extractor.py’. Please use this file for the newest version.
- Features include: MFCC, GFCC, gammatone filterbank, Power Spectrum, Log-Power Spectrum, Amplitude Modulation Spectrum(AMS, two version), Short-Time-Fourier-Transfer Spectrum.
- Utils include: Ideal Binary Mask, Ideal Ratio Mask, Speech synthesis method, Mixer by dB
- Normalizer include: zero-to-one normalizer, unit-vector normalizer.