javascript - 当检测到静音(JS)时，如何提取前面的音频(来自麦克风)作为缓冲区？

Question

我正在使用带有 NodeJS 后端的 Google Cloud API for Speech-to-text。该应用程序需要能够监听语音命令，并将它们作为缓冲区传输到后端。为此，我需要在检测到静音时发送前面音频的缓冲区。

任何帮助将不胜感激。包括下面的js代码

 if (!navigator.getUserMedia)
    navigator.getUserMedia = navigator.getUserMedia || navigator.webkitGetUserMedia ||
        navigator.mozGetUserMedia || navigator.msGetUserMedia;

if (navigator.getUserMedia) {
    navigator.getUserMedia({audio: true}, success, function (e) {
        alert('Error capturing audio.');
    });
} else alert('getUserMedia not supported in this browser.');

var recording = false;

window.startRecording = function () {
    recording = true;
};

window.stopRecording = function () {
    recording = false;
    // window.Stream.end();
};

function success(e) {
    audioContext = window.AudioContext || window.webkitAudioContext;
    context = new audioContext();

    // the sample rate is in context.sampleRate
    audioInput = context.createMediaStreamSource(e);

    var bufferSize = 4096;
    recorder = context.createScriptProcessor(bufferSize, 1, 1);

    recorder.onaudioprocess = function (e) {
        if (!recording) return;
        console.log('recording');
        var left = e.inputBuffer.getChannelData(0);
        console.log(convertoFloat32ToInt16(left));
       };

    audioInput.connect(recorder);
    recorder.connect(context.destination);
}

Answer 1

我不太确定问题中到底要问什么，所以这个答案只是为了提供一种检测音频流中静音的方法。

---

要检测音频流中的静音，您可以使用 AudioAnalyser Node ，您将在该 Node 上定期调用 getByteFrequencyData 方法，并检查在给定时间内是否有声音高于您的预期水平。

您可以直接使用 AnalyserNode 的 minDecibels 属性设置阈值级别。

function detectSilence(
  stream,
  onSoundEnd = _=>{},
  onSoundStart = _=>{},
  silence_delay = 500,
  min_decibels = -80
  ) {
  const ctx = new AudioContext();
  const analyser = ctx.createAnalyser();
  const streamNode = ctx.createMediaStreamSource(stream);
  streamNode.connect(analyser);
  analyser.minDecibels = min_decibels;

  const data = new Uint8Array(analyser.frequencyBinCount); // will hold our data
  let silence_start = performance.now();
  let triggered = false; // trigger only once per silence event

  function loop(time) {
    requestAnimationFrame(loop); // we'll loop every 60th of a second to check
    analyser.getByteFrequencyData(data); // get current data
    if (data.some(v => v)) { // if there is data above the given db limit
      if(triggered){
        triggered = false;
        onSoundStart();
        }
      silence_start = time; // set it to now
    }
    if (!triggered && time - silence_start > silence_delay) {
      onSoundEnd();
      triggered = true;
    }
  }
  loop();
}

function onSilence() {
  console.log('silence');
}
function onSpeak() {
  console.log('speaking');
}

navigator.mediaDevices.getUserMedia({
    audio: true
  })
  .then(stream => {
    detectSilence(stream, onSilence, onSpeak);
    // do something else with the stream
  })
  .catch(console.error);

还有 as a fiddle因为 stackSnippets 可能会阻止 gUM。