Day #235 - Audio Analysis

	#pip install librosa
	#pip install python_speech_features
	#librosa with python_speech_analysis
	#Credits - https://github.com/librosa/librosa/issues/573
	import librosa
	import python_speech_features
	from scipy.signal.windows import hann
	n_mfcc = 13
	n_mels = 40
	n_fft = 512 # in librosa, win_length is assumed to be equal to n_fft implicitly
	hop_length = 160
	fmin = 0
	fmax = None
	#https://librosa.github.io/librosa/generated/librosa.feature.mfcc.html
	# y - Audio Time series
	# sr - Sampling Rate
	y, sr = librosa.load(r'E:\Audio_Analytics\test_data\1_street_music.wav')
	#sr = 16000 # fake sample rate just to make the point
	# librosa
	#n_mfcc: int > 0 [scalar], number of MFCCs to return
	mfcc_librosa = librosa.feature.mfcc(y=y, sr=sr, n_fft=n_fft,
	n_mfcc=n_mfcc, n_mels=n_mels,
	hop_length=hop_length,
	fmin=fmin, fmax=fmax)
	#https://python-speech-features.readthedocs.io/en/latest/
	# python_speech_features
	# no preemph nor ceplifter in librosa, so setting to zero
	# librosa default stft window is hann
	#winlen – the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)
	#winstep – the step between successive windows in seconds. Default is 0.01s (10 milliseconds)
	#nfilt – the number of filters in the filterbank, default 26.
	#Returns: A numpy array of size (NUMFRAMES by numcep) containing features. Each row holds 1 feature vector.
	mfcc_speech = python_speech_features.mfcc(signal=y, samplerate=sr, winlen=n_fft / sr, winstep=hop_length / sr,
	numcep=n_mfcc, nfilt=n_mels, nfft=n_fft, lowfreq=fmin, highfreq=fmax,
	preemph=0, ceplifter=0, appendEnergy=False, winfunc=hann)
	print(list(mfcc_librosa[:, 0]))
	print(list(mfcc_speech[0, :]))

view raw Audio_example.py hosted with ❤ by GitHub

Happy Mastering DL!!!