Question

我创建了2个功能： - 一个记录麦克风的人 - 一个播放麦克风声音的人

录制麦克风3秒

#include <iostream>
#include <Windows.h>
#include <vector>
using namespace std;

#pragma comment(lib, "winmm.lib")

 short int waveIn[44100 * 3];

void PlayRecord();

void StartRecord()
{
const int NUMPTS = 44100 * 3;   // 3 seconds
int sampleRate = 44100;  
// 'short int' is a 16-bit type; I request 16-bit samples below
                         // for 8-bit capture, you'd use 'unsigned char' or 'BYTE' 8-bit     types

 HWAVEIN      hWaveIn;
 MMRESULT result;

 WAVEFORMATEX pFormat;
 pFormat.wFormatTag=WAVE_FORMAT_PCM;     // simple, uncompressed format
 pFormat.nChannels=1;                    //  1=mono, 2=stereo
 pFormat.nSamplesPerSec=sampleRate;      // 44100
 pFormat.nAvgBytesPerSec=sampleRate*2;   // = nSamplesPerSec * n.Channels *    wBitsPerSample/8
 pFormat.nBlockAlign=2;                  // = n.Channels * wBitsPerSample/8
 pFormat.wBitsPerSample=16;              //  16 for high quality, 8 for telephone-grade
 pFormat.cbSize=0;

 // Specify recording parameters

 result = waveInOpen(&hWaveIn, WAVE_MAPPER,&pFormat,
        0L, 0L, WAVE_FORMAT_DIRECT);

  WAVEHDR      WaveInHdr;
 // Set up and prepare header for input
  WaveInHdr.lpData = (LPSTR)waveIn;
  WaveInHdr.dwBufferLength = NUMPTS*2;
  WaveInHdr.dwBytesRecorded=0;
  WaveInHdr.dwUser = 0L;
  WaveInHdr.dwFlags = 0L;
  WaveInHdr.dwLoops = 0L;
  waveInPrepareHeader(hWaveIn, &WaveInHdr, sizeof(WAVEHDR));

 // Insert a wave input buffer
  result = waveInAddBuffer(hWaveIn, &WaveInHdr, sizeof(WAVEHDR));


 // Commence sampling input
  result = waveInStart(hWaveIn);


 cout << "recording..." << endl;

  Sleep(3 * 1000);
 // Wait until finished recording

 waveInClose(hWaveIn);

 PlayRecord();
}

void PlayRecord()
{
const int NUMPTS = 44100 * 3;   // 3 seconds
int sampleRate = 44100;  
// 'short int' is a 16-bit type; I request 16-bit samples below
                            // for 8-bit capture, you'd    use 'unsigned char' or 'BYTE' 8-bit types

HWAVEIN  hWaveIn;

WAVEFORMATEX pFormat;
pFormat.wFormatTag=WAVE_FORMAT_PCM;     // simple, uncompressed format
pFormat.nChannels=1;                    //  1=mono, 2=stereo
pFormat.nSamplesPerSec=sampleRate;      // 44100
pFormat.nAvgBytesPerSec=sampleRate*2;   // = nSamplesPerSec * n.Channels * wBitsPerSample/8
pFormat.nBlockAlign=2;                  // = n.Channels * wBitsPerSample/8
pFormat.wBitsPerSample=16;              //  16 for high quality, 8 for telephone-grade
pFormat.cbSize=0;

// Specify recording parameters

waveInOpen(&hWaveIn, WAVE_MAPPER,&pFormat, 0L, 0L, WAVE_FORMAT_DIRECT);

WAVEHDR      WaveInHdr;
// Set up and prepare header for input
WaveInHdr.lpData = (LPSTR)waveIn;
WaveInHdr.dwBufferLength = NUMPTS*2;
WaveInHdr.dwBytesRecorded=0;
WaveInHdr.dwUser = 0L;
WaveInHdr.dwFlags = 0L;
WaveInHdr.dwLoops = 0L;
waveInPrepareHeader(hWaveIn, &WaveInHdr, sizeof(WAVEHDR));

HWAVEOUT hWaveOut;
cout << "playing..." << endl;
waveOutOpen(&hWaveOut, WAVE_MAPPER, &pFormat, 0, 0, WAVE_FORMAT_DIRECT);
waveOutWrite(hWaveOut, &WaveInHdr, sizeof(WaveInHdr)); // Playing the data
Sleep(3 * 1000); //Sleep for as long as there was recorded

waveInClose(hWaveIn);
waveOutClose(hWaveOut);
}

int main()
{
 StartRecord();
    return 0;
}

如何更改我的StartRecord功能（我想我的PlayRecord功能）以使其记录，直到没有来自麦克风的输入？

（到目前为止，这2个功能完美运行 - 录制麦克风3秒钟，然后播放录音）......

谢谢！

编辑：没有声音，我的意思是声音水平太低或某事（意味着这个人可能不会说话）......

Answer 1

因为声音是波浪，它会在高压和低压之间振荡。该波形通常记录为正数和负数，零为中性压力。如果你取信号的绝对值并保持一个运行平均值就足够了。

应该在足够长的时间内取平均值，以便考虑适当的沉默量。估算平均值的一种非常便宜的方法是这样的：

const double threshold = 50;    // Whatever threshold you need
const int max_samples = 10000;  // The representative running average size

double average = 0;             // The running average
int sample_count = 0;           // When we are building the average

while( sample_count < max_samples || average > threshold ) {
    // New sample arrives, stored in 'sample'

    // Adjust the running absolute average
    if( sample_count < max_samples ) sample_count++;
    average *= double(sample_count-1) / sample_count;
    average += std::abs(sample) / sample_count;
}

较大的max_samples，较慢的average会响应信号。声音停止后，它会慢慢落下。但是，它也会缓慢上升。对于合理连续的声音来说这很好。

对于可能有短暂或长时间暂停的语音，您可能希望使用基于脉冲的方法。您可以定义预期的“静音”样本数，并在收到超过阈值的脉冲时重置它。使用上面的运行平均值和更短的窗口大小将为您提供一种检测脉冲的简单方法。那你只需要数......

const int max_samples = 100;             // Smaller window size for impulse
const int max_silence_samples = 10000;   // Maximum samples below threshold
int silence = 0;                         // Number of samples below threshold

while( silence < max_silence_samples ) {
    // Compute running average as before

    //...

    // Check for silence.  If there's a signal, reset the counter.
    if( average > threshold ) silence = 0;
    else ++silence;
}

调整threshold和max_samples将控制对弹出和点击的敏感度，而max_silence_samples可让您控制在停止录制前允许的静音程度。

毫无疑问，有更多技术方法可以实现您的目标，但首先尝试简单的方法总是好的。看看你如何使用它。

Answer 2

我建议你通过DirectShow来做。您应该创建一个麦克风，SampleGrabber，音频编码器和文件编写器的实例。你的图表应该是这样的：

麦克风 - ＆gt; SampleGrabber - ＆gt;音频编码器 - ＆gt;文件编写者

每个样本都通过SampleGrabber，您可以读取所有原始样本并检查是否应继续记录。这是您和记录并检查其内容的最佳方式。

如何在没有声音的情况下录制麦克风？

2 个答案: