def key_essentia_extractor(input_audio_file, output_text_file, **kwargs):
"""
This function estimates the overall key of an audio track.
:type input_audio_file: str
:type output_text_file: str
"""
loader = estd.MonoLoader(filename=input_audio_file,
sampleRate=kwargs["SAMPLE_RATE"])
ekey = estd.KeyExtractor(frameSize=kwargs["WINDOW_SIZE"],
hopSize=kwargs["HOP_SIZE"],
tuningFrequency=kwargs["HPCP_REFERENCE_HZ"])
key, scale, strength = ekey(loader())
result = key + '\t' + scale
textfile = open(output_text_file, 'w')
textfile.write(result + '\n')
textfile.close()
return result, strength
def key_extractor(self,
frameSize=4096,
hpcpSize=12,
maxFrequency=3500,
minFrequency=25,
windowType='hann',
profileType='bgate',
pcpThreshold=0.2,
tuningFrequency=440,
weightType='cosine'):
"""
Wrapper around essentia KeyExtractor algo. This algorithm extracts key/scale for an audio signal.
It computes HPCP frames for the input signal and applies key estimation using the Key algorithm.
Refer for more details https://essentia.upf.edu/documentation/reference/streaming_KeyExtractor.html
Returns:
a dictionary with corresponding values for key, scale and strength
eg: {'key': 'F', 'scale': 'major', 'strength': 0.7704258561134338}
"""
audio = array(self.audio_vector)
key = estd.KeyExtractor(frameSize=frameSize,
hopSize=self.hop_length,
tuningFrequency=tuningFrequency)
"""
TODO: test it with new essentia update
key = ess.KeyExtractor(frameSize=frameSize,
hopSize=self.hop_length,
sampleRate=self.fs,
hpcpSize=hpcpSize,
maxFrequency=maxFrequency,
minFrequency=minFrequency,
windowType=windowType,
profileType=profileType,
pcpThreshold=pcpThreshold,
tuningFrequency=tuningFrequency,
weightType=weightType)
"""
key, scale, strength = key.compute(audio)
return {'key': key, 'scale': scale, 'strength': strength}
def algorithm_tonal_key_essentia_basic(sound):
"""
Estimates the tonality of a given audio file.
See http://essentia.upf.edu/documentation/reference/std_KeyExtractor.html.
:param sound: sound dictionary from dataset
:return: dictionary with results per different methods
"""
results = dict()
audio = load_audio_file(file_path=sound[SOUND_FILE_KEY], sample_rate=44100)
key_extractor = estd.KeyExtractor()
key, scale, strength = key_extractor(audio)
results['EssentiaBasic'] = {
'key': '%s %s' % (key, scale),
'strength': strength
}
return results
def annotate_song(filepath):
audio = load_audio(filepath)
key, scale, key_strength = es.KeyExtractor(profileType='edma')(audio)
key_list = ['A', 'B', 'C', 'D', 'E', 'F', 'G']
# transforming bemol to sharp
if len(key) == 2 and key[1] == 'b':
cur_idx = key_list.index(key[0])
new_idx = (cur_idx - 1) % len(key_list)
new_key = key_list[new_idx] + '#'
key = new_key
# for calculating bpm, its proven that RhythmExtractor2013 works best but takes longer
rhythm_desc = es.RhythmExtractor2013()(audio)
bpm = round(rhythm_desc[0])
del audio
return {'bpm': bpm,
'key': key,
'key_scale': scale,
'key_strength': key_strength,}
import os
import essentia as e
import essentia.standard as estd
# CONFIGURATION
# ================================================================================
# Default parameters
sample_rate = 44100
window_size = 4096
hop_size = 1024
tuning_frequency = 440
# retrieve filenames from folder:
soundfiles = os.listdir(audio_folder)
if '.DS_Store' in soundfiles:
soundfiles.remove('.DS_Store')
# ANALYSIS
# ================================================================================
print "\nANALYSIS..."
for item in soundfiles:
loader = estd.MonoLoader(filename=audio_folder + '/' + item,
sampleRate=sample_rate)
key = estd.KeyExtractor(frameSize=window_size,
hopSize=hop_size,
tuningFrequency=tuning_frequency)
pool = e.Pool()
key, scale, strength = key(loader)
result = key, scale, strength
print item[:20] + '... ', result
