谷歌为WebRTC项目开发的VAD是目前最优秀、最先进和免费的产品之一。webrtcvad是WebRTC语音活动检测器(VAD)的python接口。兼容python2和python3。功能是将一段音频数据分为静音与非静音。它对于电话和语音识别很有用。
1、安装pip
yum -y install epel-release
yum -y install python-pip
2、安装webrtcvad
yum -y install python-devel
pip install webrtcvad
3、webrtcvad测试脚本（test_webrtcvad.py）
import collections
import contextlib
import sys
import wave import webrtcvad def read_wave(path):
with contextlib.closing(wave.open(path, 'rb')) as wf:
num_channels = wf.getnchannels()
assert num_channels == 1
sample_width = wf.getsampwidth()
assert sample_width == 2
sample_rate = wf.getframerate()
assert sample_rate in (8000, 16000, 32000)
pcm_data = wf.readframes(wf.getnframes())
return pcm_data, sample_rate def write_wave(path, audio, sample_rate):
with contextlib.closing(wave.open(path, 'wb')) as wf:
wf.setnchannels(1)
wf.setsampwidth(2)
wf.setframerate(sample_rate)
wf.writeframes(audio) class Frame(object):
def __init__(self, bytes, timestamp, duration):
self.bytes = bytes
self.timestamp = timestamp
self.duration = duration def frame_generator(frame_duration_ms, audio, sample_rate):
n = int(sample_rate * (frame_duration_ms / 1000.0) * 2)
offset = 0
timestamp = 0.0
duration = (float(n) / sample_rate) / 2.0
while offset + n < len(audio):
yield Frame(audio[offset:offset + n], timestamp, duration)
timestamp += duration
offset += n def vad_collector(sample_rate, frame_duration_ms,
padding_duration_ms, vad, frames):
num_padding_frames = int(padding_duration_ms / frame_duration_ms)
ring_buffer = collections.deque(maxlen=num_padding_frames)
triggered = False
voiced_frames = []
for frame in frames:
sys.stdout.write(
'' if vad.is_speech(frame.bytes, sample_rate) else '')
if not triggered:
ring_buffer.append(frame)
num_voiced = len([f for f in ring_buffer
if vad.is_speech(f.bytes, sample_rate)])
if num_voiced > 0.9 * ring_buffer.maxlen:
sys.stdout.write('+(%s)' % (ring_buffer[0].timestamp,))
triggered = True
voiced_frames.extend(ring_buffer)
ring_buffer.clear()
else:
voiced_frames.append(frame)
ring_buffer.append(frame)
num_unvoiced = len([f for f in ring_buffer
if not vad.is_speech(f.bytes, sample_rate)])
if num_unvoiced > 0.9 * ring_buffer.maxlen:
sys.stdout.write('-(%s)' % (frame.timestamp + frame.duration))
triggered = False
yield b''.join([f.bytes for f in voiced_frames])
ring_buffer.clear()
voiced_frames = []
if triggered:
sys.stdout.write('-(%s)' % (frame.timestamp + frame.duration))
sys.stdout.write('\n')
if voiced_frames:
yield b''.join([f.bytes for f in voiced_frames]) def main(args):
if len(args) != 2:
sys.stderr.write(
'Usage: example.py <aggressiveness> <path to wav file>\n')
sys.exit(1)
audio, sample_rate = read_wave(args[1])
vad = webrtcvad.Vad(int(args[0]))
frames = frame_generator(30, audio, sample_rate)
frames = list(frames)
segments = vad_collector(sample_rate, 30, 300, vad, frames)
for i, segment in enumerate(segments):
#path = 'chunk-%002d.wav' % (i,)
print('--end')
#write_wave(path, segment, sample_rate) if __name__ == '__main__':
main(sys.argv[1:])
4、运行命令（其中，第一个参数为敏感系数，取值0-3，越大表示越敏感，越激进，对细微的声音频段都可以识别出来；第二个参数为wav文件存放路径，目前仅支持8K，16K，32K的采样率，示例wav文件下载：73.wav 链接：https://pan.baidu.com/s/19YJB9u0zvCFGBLDRisK1KQ 密码：fgkf）
[root@host---- ~]# python test_webrtcvad.py /home/.wav
+(2.1)-(3.36)--end
+(3.57)-(14.43)--end
+(15.3)-(16.14)--end
+(21.21)-(22.47)--end
+(22.68)-(24.6)--end
+(24.66)-(26.76)--end
+(26.76)-(27.81)--end
+(27.87)-(31.38)--end
+(31.38)-(32.91)--end
+(33.21)-(35.04)--end
+(35.73)-(41.43)--end
+(42.66)-(43.8)--end
+(43.95)-(51.03)--end
+(51.15)-(53.82)--end
+(53.82)-(59.85)--end
+(60.51)-(64.74)--end
+(65.46)-(67.26)--end
+(67.74)-(69.39)--end
+(69.42)-(74.55)--end
+(74.55)-(81.24)--end
+(81.51)-(87.66)--end
+(87.9)-(89.76)--end
+(91.08)-(92.04)--end
+(92.31)-(96.9)--end
+(97.23)-(102.27)--end
+(102.51)-(104.43)--end
+(104.43)-(105.9)--end
+(106.38)-(108.12)--end
+(108.69)-(110.16)--end
+(111.12)-(113.13)--end
+(113.13)-(114.87)--end
+(114.87)-(118.08)--end