如何使用 AudioContext HTML5 从麦克风获取音频数据答案

【问题标题】：How do I get audio data from microphone using AudioContext HTML5如何使用 AudioContext HTML5 从麦克风获取音频数据
【发布时间】：2014-10-23 16:02:31
【问题描述】：

我正在尝试从我的麦克风获取数据流（例如音量、音高）。目前，我一直在使用getUserMedia 访问我的麦克风音频。但我找不到从中提取数据的方法。

我的代码：

$(function () {
  var audioContext = new AudioContext();
  var audioInput = null,
      realAudioInput = null,
      inputPoint = null,
      analyserNode = null;

  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.');

  function success(stream){
    inputPoint = audioContext.createGain();

    realAudioInput = audioContext.createMediaStreamSource(stream);
    audioInput = realAudioInput;
    audioInput.connect(inputPoint);

    analyserNode = audioContext.createAnalyser();
    analyserNode.fftSize = 2048;
    inputPoint.connect( analyserNode );

  }

  function live(){
    requestAnimationFrame(live);
    var freqByteData = new Uint8Array(analyserNode.frequencyBinCount);
    analyserNode.getByteFrequencyData(freqByteData);
    console.log(analyserNode.frequencyBinCount); 
  }
});

【问题讨论】：

标签： javascript html audio getusermedia audiocontext

【解决方案1】：

这是你的代码的一个版本，它做了两件事：

从发送到 console.log 的实时麦克风中检索原始 PCM 音频缓冲区（以显示 javascript 控制台点击 ctrl-shift-i ），这是时域中流式麦克风音频数据的 PCM 原始音频曲线。
它还将相同的音频数据运行到 FFT（快速傅立叶变换）中，该 FFT（快速傅立叶变换）也发送到 console.log，这是相同 Web 音频 API 事件循环缓冲区的频域表示

注意 - 戴上耳机或调低扬声器音量，否则您会听到音频反馈的尖叫声，因为麦克风会像 Jimmy Hendrix 那样拾取扬声器音频！

<html><head><meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
<title>capture microphone then show time & frequency domain output</title>

<script type="text/javascript">

var webaudio_tooling_obj = function () {

    var audioContext = new AudioContext();

    console.log("audio is starting up ...");

    var BUFF_SIZE_RENDERER = 16384;

    var audioInput = null,
    microphone_stream = null,
    gain_node = null,
    script_processor_node = null,
    script_processor_analysis_node = null,
    analyser_node = null;

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

    if (navigator.getUserMedia){

        navigator.getUserMedia({audio:true}, 
            function(stream) {
                start_microphone(stream);
            },
            function(e) {
                alert('Error capturing audio.');
            }
            );

    } else { alert('getUserMedia not supported in this browser.'); }

    // ---

    function show_some_data(given_typed_array, num_row_to_display, label) {

        var size_buffer = given_typed_array.length;
        var index = 0;

        console.log("__________ " + label);

        if (label === "time") {

            for (; index < num_row_to_display && index < size_buffer; index += 1) {

                var curr_value_time = (given_typed_array[index] / 128) - 1.0;

                console.log(curr_value_time);
            }

        } else if (label === "frequency") {

            for (; index < num_row_to_display && index < size_buffer; index += 1) {

                console.log(given_typed_array[index]);
            }

        } else {

            throw new Error("ERROR - must pass time or frequency");
        }
    }

    function process_microphone_buffer(event) {

        var i, N, inp, microphone_output_buffer;

        microphone_output_buffer = event.inputBuffer.getChannelData(0); // just mono - 1 channel for now
    }

    function start_microphone(stream){

        gain_node = audioContext.createGain();
        gain_node.connect( audioContext.destination );

        microphone_stream = audioContext.createMediaStreamSource(stream);
        microphone_stream.connect(gain_node); 

        script_processor_node = audioContext.createScriptProcessor(BUFF_SIZE_RENDERER, 1, 1);
        script_processor_node.onaudioprocess = process_microphone_buffer;

        microphone_stream.connect(script_processor_node);

        // --- enable volume control for output speakers

        document.getElementById('volume').addEventListener('change', function() {

            var curr_volume = this.value;
            gain_node.gain.value = curr_volume;

            console.log("curr_volume ", curr_volume);
        });

        // --- setup FFT

        script_processor_analysis_node = audioContext.createScriptProcessor(2048, 1, 1);
        script_processor_analysis_node.connect(gain_node);

        analyser_node = audioContext.createAnalyser();
        analyser_node.smoothingTimeConstant = 0;
        analyser_node.fftSize = 2048;

        microphone_stream.connect(analyser_node);

        analyser_node.connect(script_processor_analysis_node);

        var buffer_length = analyser_node.frequencyBinCount;

        var array_freq_domain = new Uint8Array(buffer_length);
        var array_time_domain = new Uint8Array(buffer_length);

        console.log("buffer_length " + buffer_length);

        script_processor_analysis_node.onaudioprocess = function() {

            // get the average for the first channel
            analyser_node.getByteFrequencyData(array_freq_domain);
            analyser_node.getByteTimeDomainData(array_time_domain);

            // draw the spectrogram
            if (microphone_stream.playbackState == microphone_stream.PLAYING_STATE) {

                show_some_data(array_freq_domain, 5, "frequency");
                show_some_data(array_time_domain, 5, "time"); // store this to record to aggregate buffer/file
            }
        };
    }

}(); //  webaudio_tooling_obj = function()

</script>

</head>
<body>

    <p>Volume</p>
    <input id="volume" type="range" min="0" max="1" step="0.1" value="0.5"/>

</body>
</html>

【讨论】：

感谢这对我帮助很大！
@scott 如何获取数据而不通过扬声器输出音频？
好的，我修好了。音频不是直接来自音频过程，而是来自我在网站上显示的网络摄像头视频。