File size: 2,887 Bytes
2e62044 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
import math
import numpy as np
import librosa
from utils import hparams as hp
from scipy.signal import lfilter
def label_2_float(x, bits):
return 2 * x / (2**bits - 1.) - 1.
def float_2_label(x, bits):
assert abs(x).max() <= 1.0
x = (x + 1.) * (2**bits - 1) / 2
return x.clip(0, 2**bits - 1)
def load_wav(path):
return librosa.load(path, sr=hp.sample_rate)[0]
def save_wav(x, path):
#print("path=",path)
librosa.output.write_wav(path, x.astype(np.float32), sr=hp.sample_rate)
def split_signal(x):
unsigned = x + 2**15
coarse = unsigned // 256
fine = unsigned % 256
return coarse, fine
def combine_signal(coarse, fine):
return coarse * 256 + fine - 2**15
def encode_16bits(x):
return np.clip(x * 2**15, -2**15, 2**15 - 1).astype(np.int16)
def linear_to_mel(spectrogram):
return librosa.feature.melspectrogram(
S=spectrogram, sr=hp.sample_rate, n_fft=hp.n_fft, n_mels=hp.num_mels, fmin=hp.fmin)
'''
def build_mel_basis():
return librosa.filters.mel(hp.sample_rate, hp.n_fft, n_mels=hp.num_mels, fmin=hp.fmin)
'''
def normalize(S):
return np.clip((S - hp.min_level_db) / -hp.min_level_db, 0, 1)
def denormalize(S):
return (np.clip(S, 0, 1) * -hp.min_level_db) + hp.min_level_db
def amp_to_db(x):
return 20 * np.log10(np.maximum(1e-5, x))
def db_to_amp(x):
return np.power(10.0, x * 0.05)
def spectrogram(y):
D = stft(y)
S = amp_to_db(np.abs(D)) - hp.ref_level_db
return normalize(S)
def melspectrogram(y):
D = stft(y)
S = amp_to_db(linear_to_mel(np.abs(D)))
return normalize(S)
def stft(y):
return librosa.stft(
y=y,
n_fft=hp.n_fft, hop_length=hp.hop_length, win_length=hp.win_length)
def pre_emphasis(x):
return lfilter([1, -hp.preemphasis], [1], x)
def de_emphasis(x):
return lfilter([1], [1, -hp.preemphasis], x)
def encode_mu_law(x, mu):
mu = mu - 1
fx = np.sign(x) * np.log(1 + mu * np.abs(x)) / np.log(1 + mu)
return np.floor((fx + 1) / 2 * mu + 0.5)
def decode_mu_law(y, mu, from_labels=True):
# TODO: get rid of log2 - makes no sense
if from_labels: y = label_2_float(y, math.log2(mu))
mu = mu - 1
x = np.sign(y) / mu * ((1 + mu) ** np.abs(y) - 1)
return x
def reconstruct_waveform(mel, n_iter=32):
"""Uses Griffin-Lim phase reconstruction to convert from a normalized
mel spectrogram back into a waveform."""
denormalized = denormalize(mel)
amp_mel = db_to_amp(denormalized)
S = librosa.feature.inverse.mel_to_stft(
amp_mel, power=1, sr=hp.sample_rate,
n_fft=hp.n_fft, fmin=hp.fmin)
wav = librosa.core.griffinlim(
S, n_iter=n_iter,
hop_length=hp.hop_length, win_length=hp.win_length)
return wav
|