在 Python 中檢測並記錄音頻到 PCM 格式

Question

我需要在樹莓派檢測到聲音（超過特定閾值）時以 PCM 文件格式錄制音頻，並在靜音時停止。 因此，我遇到了一個先前提出的問題，並遵循了Python 中檢測和記錄音頻中的最佳答案。 但是，它以WAV格式保存文件，但我使用的API只能讀取pcm、speex或speex-wb格式。

我怎樣才能 go 以 pcm 格式錄制音頻，同時僅在檢測到聲音時保持錄制的 function？

from sys import byteorder
from array import array
from struct import pack

import pyaudio
import wave

THRESHOLD = 8000
chans = 1
chunk = 4096
form_1 = pyaudio.paInt16
samp_rate = 44100
dev_index = 2 # device index found by p.get_device_info_by_index(ii)
wav_output_filename = 'test4.wav'

def is_silent(snd_data):
    "Returns 'True' if below the 'silent' threshold"
    return max(snd_data) < THRESHOLD

def normalize(snd_data):
    "Average the volume out"
    MAXIMUM = 16384
    times = float(MAXIMUM)/max(abs(i) for i in snd_data)

    r = array('h')
    for i in snd_data:
        r.append(int(i*times))
    return r

def trim(snd_data):
    "Trim the blank spots at the start and end"
    def _trim(snd_data):
        snd_started = False
        r = array('h')

        for i in snd_data:
            if not snd_started and abs(i)>THRESHOLD:
                snd_started = True
                r.append(i)

            elif snd_started:
                r.append(i)
        return r

    # Trim to the left
    snd_data = _trim(snd_data)

    # Trim to the right
    snd_data.reverse()
    snd_data = _trim(snd_data)
    snd_data.reverse()
    return snd_data

def add_silence(snd_data, seconds):
    "Add silence to the start and end of 'snd_data' of length 'seconds' (float)"
    silence = [0] * int(seconds * samp_rate)
    r = array('h', silence)
    r.extend(snd_data)
    r.extend(silence)
    return r

def record():
    """
    Record a word or words from the microphone and 
    return the data as an array of signed shorts.

    Normalizes the audio, trims silence from the 
    start and end, and pads with 0.5 seconds of 
    blank sound to make sure VLC et al can play 
    it without getting chopped off.
    """
    audio = pyaudio.PyAudio()
    stream = audio.open(format = form_1, channels=chans, rate = samp_rate,
                    input_device_index = dev_index, input = True, #output=True,
                    frames_per_buffer = chunk)

    num_silent = 0
    snd_started = False

    r = array('h')

    while 1:
        # little endian, signed short
        snd_data = array('h', stream.read(chunk, exception_on_overflow = False))
        if byteorder == 'big':
            snd_data.byteswap()
        r.extend(snd_data)

        silent = is_silent(snd_data)

        if silent and snd_started:
            num_silent += 1
        elif not silent and not snd_started:
            snd_started = True

        if snd_started and num_silent > 30:
            break

    sample_width = audio.get_sample_size(form_1)
    stream.stop_stream()
    stream.close()
    audio.terminate()

    r = normalize(r)
    r = trim(r)
    r = add_silence(r, 0.5)
    return sample_width, r

def record_to_file(path):
    "Records from the microphone and outputs the resulting data to 'path'"
    sample_width, data = record()
    data = pack('<' + ('h'*len(data)), *data)

    wf = wave.open(path, 'wb')
    wf.setnchannels(chans)
    wf.setsampwidth(sample_width) #
    wf.setframerate(samp_rate)
    wf.writeframes(data) #
    wf.close()

if __name__ == '__main__':
    print("please speak a word into the microphone")
    record_to_file(wav_output_filename)
    print("done - result written to " + wav_output_filename)

Answer 1

我找不到將音頻文件格式化為 pcm 的任何解決方案，但我發現我能夠以 16k 的采樣率處理 wav 格式的音頻。 所以我將保留它。