python语音引擎深度学习_python深度学习之语音识别(speech recognize)

问题描述

speech recognize是kaggle上1，2年前的一个赛题，主要描述的是如果在各种环境中识别出简单的英文单词发音，比如bed，cat，right之类的语音。提供的训练集是.wav格式的语音，解压后数据集大小在2G左右。

训练集分析

语音识别相对图片识别来说，是一个区别较大的领域。所以首先要了解训练集的基本特征，理清不同语音之间的共性。

振幅和频率

def log_specgram(audio, sample_rate, window_size=20,

step_size=10, eps=1e-10):

nperseg = int(round(window_size * sample_rate / 1e3))

noverlap = int(round(step_size * sample_rate / 1e3))

freqs, times, spec = signal.spectrogram(audio,

fs=sample_rate,

window='hann',

nperseg=nperseg,

noverlap=noverlap,

detrend=False)

return freqs, times, np.log(spec.T.astype(np.float32) + eps)

def plt_specgram(freqs, times, spectrogram):

fig = plt.figure(figsize=(14, 8))

ax1 = fig.add_subplot(211)

ax1.set_title('Raw wave of ' + filename)

ax1.set_ylabel('Amplitude')

ax1.plot(np.linspace(0, sample_rate / len(samples), sample_rate), samples)

ax2 = fig.add_subplot(212)

ax2.imshow(spectrogram.T, aspect='auto', origin='lower',

extent=[times.min(), times.max(), freqs.min(), freqs.max()])

ax2.set_yticks(freqs[::16])

ax2.set_xticks(times[::16])

ax2.set_title('Spectrogram of ' + filename)

ax2.set_ylabel('Freqs in Hz')

ax2.set_xlabel('Seconds')

plt.savefig('./output/yes_0a7c2a8d_nohash_0.png')

plt.show()

train_audio_path = './input/train/audio/'

filename = '/yes/0a7c2a8d_nohash_0.wav'

sample_rate, samples = wavfile.read(str(train_audio_path) + filename)

# print(sample_rate, samples)

# 频谱图

freqs, times, spectrogram = log_specgram(samples, sample_rate)

plt_specgram(freqs, times, spectrogram)

声音强度

def plt_spectrogram():

plt.figure(figsize=(12, 4))

librosa.display.specshow(log_S, sr=sample_rate, x_axis='time', y_axis='mel')

plt.title('Mel power spectrogram ')

plt.colorbar(format='%+02.0f dB')

plt.tight_layout()

plt.savefig('./output/spectrogram.png')

plt.show()

# 光谱图

sig = samples

sig = sig / max(abs(sig))

S = librosa.feature.melspectrogram(y=sig, sr=sample_rate, n_mels=128)

log_S = librosa.power_to_db(S, ref=np.max)

plt_spectrogram()