如何使用 pyaudio 检测来自现场麦克风的突然敲击噪音？
问问题
36019 次
2 回答
102
我做过的一种方法：
- 一次读取一组样本，例如 0.05 秒
- 计算块的 RMS 幅度（单个样本的平方平均值的平方根）
- 如果块的 RMS 幅度大于阈值，则为“嘈杂块”，否则为“安静块”
- 突然敲击将是一个安静的街区，然后是少量嘈杂的街区，然后是一个安静的街区
- 如果你从来没有得到一个安静的街区，你的门槛太低了
- 如果你从来没有得到一个嘈杂的街区，你的门槛太高了
我的应用程序在无人看管的情况下录制“有趣”的噪音，所以只要有嘈杂的块，它就会记录下来。如果有 15 秒的嘈杂时间（“捂住耳朵”），它将阈值乘以 1.1，如果有 15分钟的安静时间（“更努力地听”），它将阈值乘以 0.9。您的应用程序将有不同的需求。
另外，刚刚注意到我的代码中关于观察到的 RMS 值的一些注释。在 Macbook Pro 的内置麦克风上，具有 +/- 1.0 标准化音频数据范围，输入音量设置为最大，一些数据点：
- 0.003-0.006（-50dB 到 -44dB）我家的中央供暖风扇声音非常大
- 0.010-0.40（-40dB 到 -8dB）在同一台笔记本电脑上打字
- 0.10 (-20dB) 在 1' 距离处轻柔地弹响手指
- 0.60 (-4.4dB) 在 1' 处大声弹响手指
更新：这是一个让您入门的示例。
#!/usr/bin/python
# open a microphone in pyAudio and listen for taps
import pyaudio
import struct
import math
INITIAL_TAP_THRESHOLD = 0.010
FORMAT = pyaudio.paInt16
SHORT_NORMALIZE = (1.0/32768.0)
CHANNELS = 2
RATE = 44100
INPUT_BLOCK_TIME = 0.05
INPUT_FRAMES_PER_BLOCK = int(RATE*INPUT_BLOCK_TIME)
# if we get this many noisy blocks in a row, increase the threshold
OVERSENSITIVE = 15.0/INPUT_BLOCK_TIME
# if we get this many quiet blocks in a row, decrease the threshold
UNDERSENSITIVE = 120.0/INPUT_BLOCK_TIME
# if the noise was longer than this many blocks, it's not a 'tap'
MAX_TAP_BLOCKS = 0.15/INPUT_BLOCK_TIME
def get_rms( block ):
# RMS amplitude is defined as the square root of the
# mean over time of the square of the amplitude.
# so we need to convert this string of bytes into
# a string of 16-bit samples...
# we will get one short out for each
# two chars in the string.
count = len(block)/2
format = "%dh"%(count)
shorts = struct.unpack( format, block )
# iterate over the block.
sum_squares = 0.0
for sample in shorts:
# sample is a signed short in +/- 32768.
# normalize it to 1.0
n = sample * SHORT_NORMALIZE
sum_squares += n*n
return math.sqrt( sum_squares / count )
class TapTester(object):
def __init__(self):
self.pa = pyaudio.PyAudio()
self.stream = self.open_mic_stream()
self.tap_threshold = INITIAL_TAP_THRESHOLD
self.noisycount = MAX_TAP_BLOCKS+1
self.quietcount = 0
self.errorcount = 0
def stop(self):
self.stream.close()
def find_input_device(self):
device_index = None
for i in range( self.pa.get_device_count() ):
devinfo = self.pa.get_device_info_by_index(i)
print( "Device %d: %s"%(i,devinfo["name"]) )
for keyword in ["mic","input"]:
if keyword in devinfo["name"].lower():
print( "Found an input: device %d - %s"%(i,devinfo["name"]) )
device_index = i
return device_index
if device_index == None:
print( "No preferred input found; using default input device." )
return device_index
def open_mic_stream( self ):
device_index = self.find_input_device()
stream = self.pa.open( format = FORMAT,
channels = CHANNELS,
rate = RATE,
input = True,
input_device_index = device_index,
frames_per_buffer = INPUT_FRAMES_PER_BLOCK)
return stream
def tapDetected(self):
print("Tap!")
def listen(self):
try:
block = self.stream.read(INPUT_FRAMES_PER_BLOCK)
except IOError as e:
# dammit.
self.errorcount += 1
print( "(%d) Error recording: %s"%(self.errorcount,e) )
self.noisycount = 1
return
amplitude = get_rms( block )
if amplitude > self.tap_threshold:
# noisy block
self.quietcount = 0
self.noisycount += 1
if self.noisycount > OVERSENSITIVE:
# turn down the sensitivity
self.tap_threshold *= 1.1
else:
# quiet block.
if 1 <= self.noisycount <= MAX_TAP_BLOCKS:
self.tapDetected()
self.noisycount = 0
self.quietcount += 1
if self.quietcount > UNDERSENSITIVE:
# turn up the sensitivity
self.tap_threshold *= 0.9
if __name__ == "__main__":
tt = TapTester()
for i in range(1000):
tt.listen()
于 2010-11-12T00:58:12.183 回答
17
上述代码的简化版本...
import pyaudio
import struct
import math
INITIAL_TAP_THRESHOLD = 0.010
FORMAT = pyaudio.paInt16
SHORT_NORMALIZE = (1.0/32768.0)
CHANNELS = 2
RATE = 44100
INPUT_BLOCK_TIME = 0.05
INPUT_FRAMES_PER_BLOCK = int(RATE*INPUT_BLOCK_TIME)
OVERSENSITIVE = 15.0/INPUT_BLOCK_TIME
UNDERSENSITIVE = 120.0/INPUT_BLOCK_TIME # if we get this many quiet blocks in a row, decrease the threshold
MAX_TAP_BLOCKS = 0.15/INPUT_BLOCK_TIME # if the noise was longer than this many blocks, it's not a 'tap'
def get_rms(block):
# RMS amplitude is defined as the square root of the
# mean over time of the square of the amplitude.
# so we need to convert this string of bytes into
# a string of 16-bit samples...
# we will get one short out for each
# two chars in the string.
count = len(block)/2
format = "%dh"%(count)
shorts = struct.unpack( format, block )
# iterate over the block.
sum_squares = 0.0
for sample in shorts:
# sample is a signed short in +/- 32768.
# normalize it to 1.0
n = sample * SHORT_NORMALIZE
sum_squares += n*n
return math.sqrt( sum_squares / count )
pa = pyaudio.PyAudio() #]
#|
stream = pa.open(format = FORMAT, #|
channels = CHANNELS, #|---- You always use this in pyaudio...
rate = RATE, #|
input = True, #|
frames_per_buffer = INPUT_FRAMES_PER_BLOCK) #]
tap_threshold = INITIAL_TAP_THRESHOLD #]
noisycount = MAX_TAP_BLOCKS+1 #|---- Variables for noise detector...
quietcount = 0 #|
errorcount = 0 #]
for i in range(1000):
try: #]
block = stream.read(INPUT_FRAMES_PER_BLOCK) #|
except IOError, e: #|---- just in case there is an error!
errorcount += 1 #|
print( "(%d) Error recording: %s"%(errorcount,e) ) #|
noisycount = 1 #]
amplitude = get_rms(block)
if amplitude > tap_threshold: # if its to loud...
quietcount = 0
noisycount += 1
if noisycount > OVERSENSITIVE:
tap_threshold *= 1.1 # turn down the sensitivity
else: # if its to quiet...
if 1 <= noisycount <= MAX_TAP_BLOCKS:
print 'tap!'
noisycount = 0
quietcount += 1
if quietcount > UNDERSENSITIVE:
tap_threshold *= 0.9 # turn up the sensitivity
于 2012-05-19T21:43:00.567 回答