forked from Open-CT/opendata
82 lines
3.4 KiB
Python
82 lines
3.4 KiB
Python
import librosa
|
|
import numpy as np
|
|
import os
|
|
import csv
|
|
|
|
|
|
def extract_audio_feature(path):
|
|
y, sr = librosa.load(path, mono=True, sr=None)
|
|
chroma_stft = librosa.feature.chroma_stft(y=y, sr=sr)
|
|
rmse = librosa.feature.rms(y=y)
|
|
spec_cent = librosa.feature.spectral_centroid(y=y, sr=sr)
|
|
spec_bw = librosa.feature.spectral_bandwidth(y=y, sr=sr)
|
|
rolloff = librosa.feature.spectral_rolloff(y=y, sr=sr)
|
|
zcr = librosa.feature.zero_crossing_rate(y)
|
|
mfcc = librosa.feature.mfcc(y=y, sr=sr)
|
|
features = f'{np.mean(chroma_stft)} {np.mean(rmse)} {np.mean(spec_cent)} {np.mean(spec_bw)} {np.mean(rolloff)} {np.mean(zcr)}'
|
|
for e in mfcc:
|
|
features += f' {np.mean(e)}'
|
|
return features
|
|
def preprocess_ravdess2():
|
|
header = 'filename chroma_stft rmse spectral_centroid spectral_bandwidth rolloff zero_crossing_rate'
|
|
for i in range(1, 21):
|
|
header += f' mfcc{i}'
|
|
header += ' label'
|
|
header = header.split()
|
|
|
|
file = open('../Output/only_class_data.csv', 'a', newline='')
|
|
with file:
|
|
writer = csv.writer(file)
|
|
writer.writerow(header)
|
|
for label in os.listdir(f'class'):
|
|
if label != '_desktop.ini':
|
|
print('label',label)
|
|
for audio in os.listdir(f'class/{label}'):
|
|
print('audio',audio)
|
|
if audio.split('.')[-1] == 'wav' and audio != '_desktop.ini':
|
|
audio_path = f'class/{label}/{audio}'
|
|
print(audio_path)
|
|
to_append = f'{"0809"}_{label}_{audio}'
|
|
features = extract_audio_feature(audio_path)
|
|
to_append += f' {features}'
|
|
to_append += f' {label}'
|
|
file = open('../Output/only_class_data.csv', 'a', newline='')
|
|
with file:
|
|
writer = csv.writer(file)
|
|
writer.writerow(to_append.split())
|
|
|
|
def preprocess_ravdess():
|
|
header = 'filename chroma_stft rmse spectral_centroid spectral_bandwidth rolloff zero_crossing_rate'
|
|
for i in range(1, 21):
|
|
header += f' mfcc{i}'
|
|
header += ' label'
|
|
header = header.split()
|
|
|
|
# file = open('../Output/only_casia.csv', 'w+', newline='')
|
|
# with file:
|
|
# writer = csv.writer(file)
|
|
# writer.writerow(header)
|
|
emotions = 'neutral calm happy sad angry fear disgust surprise'.split()
|
|
for actor in os.listdir(r'casia'):
|
|
print('actor',actor)
|
|
for label in os.listdir(f'casia/{actor}'):
|
|
if label != '_desktop.ini':
|
|
print('label',label)
|
|
for audio in os.listdir(f'casia/{actor}/{label}'):
|
|
print('audio',audio)
|
|
if audio.split('.')[-1] == 'wav' and audio != '_desktop.ini':
|
|
audio_path = f'casia/{actor}/{label}/{audio}'
|
|
print(audio_path)
|
|
to_append = f'{actor}_{label}_{audio}'
|
|
features = extract_audio_feature(audio_path)
|
|
to_append += f' {features}'
|
|
to_append += f' {label}'
|
|
file = open('../Output/english_casia.csv', 'a', newline='')
|
|
with file:
|
|
writer = csv.writer(file)
|
|
writer.writerow(to_append.split())
|
|
|
|
|
|
if __name__ == '__main__':
|
|
preprocess_ravdess()
|
|
# preprocess_ravdess2() |