Question

我正在为设备测试系统。我要确保从被测设备播放特定的声音效果。

为验证这一点，我打算使用一台运行Linux的小型计算机。

目标是使用Python打开麦克风并收听波形格式的声音效果。

我发现一个名为pyaudio的库似乎是一个不错的开始。我发现这个例子可以从麦克风读取原始数据： Reading input sound signal using Python

我还找到了检测拍手https://github.com/xSparfuchs/clap-detection/blob/master/clap-detection.py

的示例

import pyaudio
import struct
import math

INITIAL_TAP_THRESHOLD = 0.25
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): #DETECTED
        print ("tapped")

    def listen(self):
        try:
            block = self.stream.read(INPUT_FRAMES_PER_BLOCK)
        except 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
        else:            
            # quiet block.

            if 1 <= self.noisycount <= MAX_TAP_BLOCKS:
                self.tapDetected()
            self.noisycount = 0
            self.quietcount += 1

if __name__ == "__main__":
    tt = TapTester()

    for i in range(1000):
        tt.listen()

但是我想要的是一些更复杂的东西，可以实际识别出我作为.wav文件具有的特定声音效果。如果可能的话，我什至需要检测两种或两种不同的声音效果。

所以问题是，这是否足够容易构建自己，在这种情况下，我需要获取有关可以用于识别部分的算法/函数的一些信息。另外，如果有一些可用的库，可能是一个不错的解决方法。

使用麦克风收听声音效果

0 个答案: