# -*- encoding:utf-8 -*-
import numpy as np
import numpy.fft as nf
import scipy.io.wavfile as wf
import matplotlib.pyplot as plt
sample_rate, sigs = wf.read('../machine_learning_date/freq.wav')
print(sample_rate)   # 8000采樣率
print(sigs.shape)  # (3251,)
sigs = sigs / (2 ** 15) # 歸一化
times = np.arange(len(sigs)) / sample_rate
freqs = nf.fftfreq(sigs.size, 1 / sample_rate)
ffts = nf.fft(sigs)
pows = np.abs(ffts)
plt.figure('Audio')
plt.subplot(121)
plt.title('Time Domain')
plt.xlabel('Time', fontsize=12)
plt.ylabel('Signal', fontsize=12)
plt.tick_params(labelsize=10)
plt.grid(linestyle=':')
plt.plot(times, sigs, c='dodgerblue', label='Signal')
plt.legend()
plt.subplot(122)
plt.title('Frequency Domain')
plt.xlabel('Frequency', fontsize=12)
plt.ylabel('Power', fontsize=12)
plt.tick_params(labelsize=10)
plt.grid(linestyle=':')
plt.plot(freqs[freqs >= 0], pows[freqs >= 0], c='orangered', label='Power')
plt.legend()
plt.tight_layout()
plt.show()

import scipy.io.wavfile as wf
import python_speech_features as sf
sample_rate, sigs = wf.read('../data/freq.wav')
mfcc = sf.mfcc(sigs, sample_rate)

python -m pip install python_speech_features
import scipy.io.wavfile as wf
import python_speech_features as sf
import matplotlib.pyplot as mp
sample_rate, sigs = wf.read(
  '../ml_data/speeches/training/banana/banana01.wav')
mfcc = sf.mfcc(sigs, sample_rate)
mp.matshow(mfcc.T, cmap='gist_rainbow')
mp.show()

import hmmlearn.hmm as hl
model = hl.GaussianHMM(n_components=4, covariance_type='diag', n_iter=1000)
# n_components: 用幾個(gè)高斯分布函數(shù)擬合樣本數(shù)據(jù)
# covariance_type: 相關(guān)矩陣的輔對(duì)角線進(jìn)行相關(guān)性比較
# n_iter: 最大迭代上限
model.fit(mfccs) # 使用模型匹配測(cè)試mfcc矩陣的分值 score = model.score(test_mfccs)

import os
import numpy as np
import scipy.io.wavfile as wf
import python_speech_features as sf
import hmmlearn.hmm as hl
​
#1. 讀取training文件夾中的訓(xùn)練音頻樣本，每個(gè)音頻對(duì)應(yīng)一個(gè)mfcc矩陣，每個(gè)mfcc都有一個(gè)類別（apple）。
def search_file(directory):
  # 使傳過來的directory匹配當(dāng)前操作系統(tǒng)
  # {'apple':[url, url, url ... ], 'banana':[...]}  
  directory = os.path.normpath(directory)
  objects = {}
  # curdir：當(dāng)前目錄 
  # subdirs: 當(dāng)前目錄下的所有子目錄
  # files: 當(dāng)前目錄下的所有文件名
  for curdir, subdirs, files in os.walk(directory):
    for file in files:
      if file.endswith('.wav'):
        label = curdir.split(os.path.sep)[-1]
        if label not in objects:
          objects[label] = []
        # 把路徑添加到label對(duì)應(yīng)的列表中
        path = os.path.join(curdir, file)
        objects[label].append(path)
  return objects
​
#讀取訓(xùn)練集數(shù)據(jù)
train_samples = \
  search_file('../ml_data/speeches/training')
​
'''

 | mfcc |    |
  | mfcc | apple |
  | mfcc |    |
  .....
  由上述訓(xùn)練集樣本可以訓(xùn)練一個(gè)用于匹配apple的HMM。
'''
train_x, train_y = [], []
# 遍歷7次 apple/banana/...
for label, filenames in train_samples.items():
  mfccs = np.array([])
  for filename in filenames:
    sample_rate, sigs = wf.read(filename)
    mfcc = sf.mfcc(sigs, sample_rate)
    if len(mfccs)==0:
      mfccs = mfcc
    else:
      mfccs = np.append(mfccs, mfcc, axis=0)
  train_x.append(mfccs)
  train_y.append(label)
'''
訓(xùn)練集:
  train_x train_y
  ----------------
  | mfcc |    |
  | mfcc | apple |
  | mfcc |    |
  ----------------
  | mfcc |    |
  | mfcc | banana |
  | mfcc |    |
  -----------------
  | mfcc |    |
  | mfcc | lime  |
  | mfcc |    |
  -----------------
'''
# {'apple':object, 'banana':object ...}
models = {}
for mfccs, label in zip(train_x, train_y):
  model = hl.GaussianHMM(n_components=4, 
    covariance_type='diag', n_iter=1000)
  models[label] = model.fit(mfccs)
'''

'''
#讀取測(cè)試集數(shù)據(jù)
test_samples = \
  search_file('../ml_data/speeches/testing')
​
test_x, test_y = [], []
for label, filenames in test_samples.items():
  mfccs = np.array([])
  for filename in filenames:
    sample_rate, sigs = wf.read(filename)
    mfcc = sf.mfcc(sigs, sample_rate)
    if len(mfccs)==0:
      mfccs = mfcc
    else:
      mfccs = np.append(mfccs, mfcc, axis=0)
  test_x.append(mfccs)
  test_y.append(label)
​
'''測(cè)試集：
  test_x test_y
  -----------------
  | mfcc | apple |
  -----------------
  | mfcc | banana |
  -----------------
  | mfcc | lime  |
  -----------------
'''
pred_test_y = []
for mfccs in test_x:
# 判斷mfccs與哪一個(gè)HMM模型更加匹配
best_score, best_label = None, None
for label, model in models.items():
score = model.score(mfccs)
if (best_score is None) or (best_score<score):
best_score = score
best_label = label
pred_test_y.append(best_label)
​
print(test_y)
print(pred_test_y)

import json
import numpy as np
import scipy.io.wavfile as wf
with open('../data/12.json', 'r') as f:
  freqs = json.loads(f.read())
tones = [
  ('G5', 1.5),
  ('A5', 0.5),
  ('G5', 1.5),
  ('E5', 0.5),
  ('D5', 0.5),
  ('E5', 0.25),
  ('D5', 0.25),
  ('C5', 0.5),
  ('A4', 0.5),
  ('C5', 0.75)]
sample_rate = 44100
music = np.empty(shape=1)
for tone, duration in tones:
  times = np.linspace(0, duration, duration * sample_rate)
  sound = np.sin(2 * np.pi * freqs[tone] * times)
  music = np.append(music, sound)
music *= 2 ** 15
music = music.astype(np.int16)
wf.write('../data/music.wav', sample_rate, music)