os.chdir('..')
if os.path.exists(os.path.join(os.getcwd(), folder_name)):
shutil.rmtree(os.path.join(os.getcwd(), folder_name))
os.makedirs(os.path.join(os.getcwd(), folder_name))
os.chdir(os.path.join(os.getcwd(), folder_name))
return os.getcwd()
filepath = '/Users/harrison/Desktop/Thesis_Test/Kesha - Cmon copy/Stems'
csv_path = create_folder_above(filepath)
for stem in os.listdir(filepath):
file_name, file_extension = os.path.splitext(stem)
if file_extension == '.wav':
# Get discretized audio to run through features
print "Importing %s for analysis" % file_name
data, fs, t = feature_extraction.import_audio(os.path.join(filepath, stem))
# Calculate Dynamics Features
print "Calculating dynamics features for %s" % file_name
loudness_momentary, t_ = feature_extraction.calc_loudness(data, measurement = 'momentary')
print "done!"
loudness_short, t_ = feature_extraction.calc_loudness(data, measurement = 'short')
print "done!"
loudness_integrated = feature_extraction.calc_loudness(data, measurement = 'integrated')
print "done!"
lra = feature_extraction.calc_loudness(data, measurement = 'lra')
print "done!"
crest_factor_1s, t_ = feature_extraction.calc_crest_factor(data, win_size=1000, fs=44100)
print "done!"
crest_factor_100ms, t_ = feature_extraction.calc_crest_factor(data, win_size=100, fs=44100)
print "done!"
def normalize_multitracks(filepath):
"""
filepath: string pointing to audio file on disk
This function takes a directory of .wav multi-track files
and normalizes them such that the track with the highest peak-level
is normalized as normal, and then all other tracks are raised
the same amount of dB as the track with the highest peak-level.
returns: A new directory of normalized data
"""
peak_amplitudes = []
tracks = os.listdir(filepath)
norm_path = filepath + "/normalized_tracks"
# Create the normalized data folder to house all our normalized data
print("Creating folder to store normalized data")
create_folder(norm_path)
# Scan tracks, and get the peak amplitudes of each track
for track in tracks:
file_name, file_extension = os.path.splitext(track)
if file_extension == '.wav':
data, fs, t = feature_extraction.import_audio(filepath + "/" + track)
peak_amplitude = calc_peak(data)
peak_amplitudes.append(peak_amplitude)
# Find the highest amplitude track by index
idxs_norm = np.argwhere(peak_amplitudes == np.amax(peak_amplitudes))
idxs_norm = idxs_norm.flatten().tolist()
# Normalize the highest amplitude tracks and write them out
track_num = -1
for track in tracks:
file_name, file_extension = os.path.splitext(track)
if file_extension == '.wav':
track_num += 1
if track_num in idxs_norm:
data, fs, t = feature_extraction.import_audio(filepath + "/" + track)
write_path = (norm_path + "/" + file_name + "_normalized" + file_extension)
print("Normalizing %s") % track
librosa.output.write_wav(write_path, data, sr=44100, norm=True)
# Find the indexes of all the other tracks that need to be raised relative to those normalized to 0
idxs_relative = np.argwhere(peak_amplitudes != np.amax(peak_amplitudes))
idxs_relative = idxs_relative.flatten().tolist()
# This value will be used to scale all other tracks to those normalized
scalar = np.amax(peak_amplitudes)
# Raise the amplitude of all tracks the same amount that those normalized to 0 were raised
track_num = -1
for track in tracks:
file_name, file_extension = os.path.splitext(track)
if file_extension == '.wav':
track_num += 1
if track_num in idxs_relative:
data, fs, t = feature_extraction.import_audio(filepath + "/" + track)
# Perform the Relative Normalization
data = data/scalar
write_path = (norm_path + "/" + file_name + "_normalized" + file_extension)
print("Normalizing %s") % track
librosa.output.write_wav(write_path, data, sr=44100, norm=False)
