Python实现语音识别和语音合成功能

# -*- 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采样率
print(sigs.shape)  # (3251,)
sigs = sigs / (2 ** 15) # 归一化
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: 用几个高斯分布函数拟合样本数据
# covariance_type: 相关矩阵的辅对角线进行相关性比较
# n_iter: 最大迭代上限
model.fit(mfccs) # 使用模型匹配测试mfcc矩阵的分值 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
"htmlcode">

 | mfcc |    |
  | mfcc | apple |
  | mfcc |    |
  .....
  由上述训练集样本可以训练一个用于匹配apple的HMM。
'''
train_x, train_y = [], []
# 遍历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)
'''
训练集:
  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)
'''


4. 读取testing文件夹中的测试样本，针对每一个测试样本：
   1. 分别使用7个HMM模型，对测试样本计算score得分。
   2. 取7个模型中得分最高的模型所属类别作为预测类别。



'''
#读取测试集数据
test_samples =   search_file('../ml_data/speeches/testing')
"color: #ff0000">声音合成

根据需求获取某个声音的模型频域数据，根据业务需要可以修改模型数据，逆向生成时域数据，完成声音的合成。
案例：


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)


总结
以上所述是小编给大家介绍的Python实现语音识别和语音合成功能,希望对大家有所帮助，如果大家有任何疑问请给我留言，小编会及时回复大家的。在此也非常感谢大家对网站的支持！

如果你觉得本文对你有帮助，欢迎转载，烦请注明出处，谢谢！