def extract_mfcc(input_wav_dir, output_feature_file, output_feature_dir):
# secure destination
mkdir_for_file(output_feature_file)
mkdir_for_dir(output_feature_dir)
# extract mfcc in single file format and dir format
import util
mkdir_for_dir(default_temp_dir)
util.make_feature(input_wav_dir, default_temp_dir)
def write_feat(feat, feat_id, outfile):
outfile.write(feat_id+'.wav\n')
for i in range(feat.shape[0]):
fline = '{:04d} {:04d} #' + ' {:f}'*feat.shape[1] +'\n'
outfile.write(fline.format(i, i+1, *feat[i]))
outfile.write('\n')
with open(output_feature_file, 'w') as outfile:
for f in sorted(os.listdir(default_temp_dir)):
feat = util.read_feature(os.path.join(default_temp_dir, f))
write_feat(feat, f[:-4], outfile)
for f in sorted(os.listdir(default_temp_dir)):
feat = util.read_feature(os.path.join(default_temp_dir, f))
util.write_feature(feat, os.path.join(output_feature_dir, f))
# cleanup, remove large files
mkdir_for_dir(default_temp_dir)
import sys
import numpy as np
sys.path.insert(0, "zrst/")
from util import write_feature
feat = open(sys.argv[1], "r")
outfile = ""
for line in feat:
line = line.rstrip("\n")
if "wav" in line:
outfile = sys.argv[2] + "/" + line[:-3] + "mfc"
mfc = []
continue
if line == "":
feature = np.asarray(mfc)
write_feature(feature, outfile, period=100000)
tokens = line.split()
mfc.append([float(i) for i in tokens[3:]])
def write_feature_dir(feat, feat_id, feature_dir):
import util
for feature, id in zip(feat, feat_id):
util.write_feature(feature, os.path.join(feature_dir, id+'.mfc'))