使用来自现场麦克风的pyaudio检测点击

我这样做的一种方式：

• 一次读取一块样本，比如说值得0.05秒
• 计算块的RMS幅度（各个样本的平方的平均值的平方根）
• 如果块的RMS幅度大于阈值，则为“嘈杂的块”，否则为“安静的块”
• 突然的敲击将是一个安静的区域，然后是少量的噪音区域，然后是一个安静的区域
• 如果您从不安静，则门槛太低
• 如果您从不听到嘈杂的声音，则您的门槛太高

我的应用程序正在录制无人看管的“有趣”噪音，因此只要有嘈杂的声音，它就会录制下来。如果有15秒的嘈杂时间（“遮住耳朵”），则将阈值乘以1.1；如果有15
分钟的 安静时间（“更难听”），则将阈值乘以0.9 。您的应用程序将有不同的需求。

此外，刚刚注意到我的代码中有关观察到的RMS值的一些注释。在Macbook Pro的内置麦克风上，标准化的音频数据范围为+/-
1.0，输入音量设置为max，一些数据点：

• 0.003-0.006（-50dB至-44dB）我家的中央暖气风扇
• 在同一台笔记本电脑上键入0.010-0.40（-40dB至-8dB）
• 0.10（-20dB）在1’距离处轻柔地d指
• 0.60（-4.4dB）在1’处大声响动

更新：这是一个入门的示例。

#!/usr/bin/python# open a microphone in pyAudio and listen for tapsimport pyaudioimport structimport mathINITIAL_TAP_THRESHOLD = 0.010FORMAT = pyaudio.paInt16 SHORT_NORMALIZE = (1.0/32768.0)CHANNELS = 2RATE = 44100  INPUT_BLOCK_TIME = 0.05INPUT_frameS_PER_BLOCK = int(RATE*INPUT_BLOCK_TIME)# if we get this many noisy blocks in a row, increase the thresholdOVERSENSITIVE = 15.0/INPUT_BLOCK_TIME         # if we get this many quiet blocks in a row, decrease the thresholdUNDERSENSITIVE = 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_TIMEdef 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 *= 0.9if __name__ == "__main__":    tt = TapTester()    for i in range(1000):        tt.listen()