python-speech-features

import numpy as np from scipy.io import wavfile from python_speech_features import mfcc, logfbank import os # Create a dummy WAV file for demonstration samplerate = 16000 # Hz duration = 1 # seconds f_hz = 440 # A4 note t = np.linspace(0., duration, int(samplerate * duration)) signal = 0.5 * np.sin(2 * np.pi * f_hz * t) # Scale to 16-bit integer for WAV file wav_signal = (signal * 32767).astype(np.int16) dummy_wav_filename = 'dummy_audio.wav' wavfile.write(dummy_wav_filename, samplerate, wav_signal) # Read the audio file (rate, sig) = wavfile.read(dummy_wav_filename) # Compute MFCC features mfcc_feat = mfcc(sig, rate) print(f"MFCC features shape: {mfcc_feat.shape}") # Compute Log Filterbank energies fbank_feat = logfbank(sig, rate) print(f"Log Filterbank features shape: {fbank_feat.shape}") # Clean up the dummy file os.remove(dummy_wav_filename)