将缓冲区输入中的音频从 48000 下采样到 16000答案

【问题标题】：Downsample the audio from buffer inputs from 48000 to 16000将缓冲区输入中的音频从 48000 下采样到 16000
【发布时间】：2018-12-17 06:40:06
【问题描述】：

我有 recorder.js 它将记录音频并接受缓冲区输入，但我想 downsample 音频缓冲区但我很困惑在哪里调用它我已经写好了。请检查我的函数，如果可能，请建议在哪里调用它。

import InlineWorker from 'inline-worker';

export class Recorder {
    config = {
        bufferLen: 4096,
        numChannels: 2,
        mimeType: 'audio/mp3'
    };

    recording = false;

    callbacks = {
        getBuffer: [],
        exportWAV: []
    };

    constructor(source, cfg) {
        Object.assign(this.config, cfg);
        this.context = source.context;
        this.node = (this.context.createScriptProcessor ||
        this.context.createJavaScriptNode).call(this.context,
            this.config.bufferLen, this.config.numChannels, this.config.numChannels);

        this.node.onaudioprocess = (e) => {
            if (!this.recording) return;

            var buffer = [];
            for (var channel = 0; channel < this.config.numChannels; channel++) {
                buffer.push(e.inputBuffer.getChannelData(channel));
            }
            this.worker.postMessage({
                command: 'record',
                buffer: buffer
            });
        };

        source.connect(this.node);
        this.node.connect(this.context.destination);    //this should not be necessary

        let self = {};
        this.worker = new InlineWorker(function () {
            let recLength = 0,
                recBuffers = [],
                sampleRate,
                numChannels;

            this.onmessage = function (e) {
                switch (e.data.command) {
                    case 'init':
                        init(e.data.config);
                        break;
                    case 'record':
                        record(e.data.buffer);
                        break;
                    case 'exportWAV':
                        exportWAV(e.data.type);
                        break;
                    case 'getBuffer':
                        getBuffer();
                        break;
                    case 'clear':
                        clear();
                        break;
                }
            };

            function init(config) {
                sampleRate = config.sampleRate;
                numChannels = config.numChannels;
                initBuffers();
            }

            function record(inputBuffer) {
                for (var channel = 0; channel < numChannels; channel++) {
                    recBuffers[channel].push(inputBuffer[channel]);
                }
                recLength += inputBuffer[0].length;
            }

             function exportWAV(type) {
            let buffers = [];
            for (let channel = 0; channel < numChannels; channel++) {
                buffers.push(mergeBuffers(recBuffers[channel], recLength));
            }
            let interleaved;
            if (numChannels === 2) {
                interleaved = interleave(downsampleBuffer(buffers[0]), downsampleBuffer(buffers[1]));
            } else {
                interleaved = buffers[0];
            }

            let dataview = encodeWAV(interleaved);
            let audioBlob = new Blob([dataview], {type: type});

            this.postMessage({command: 'exportWAV', data: audioBlob});
        }


    function downsampleBuffer(buffer) {
        if (16000 === sampleRate) {
          return buffer;
        }
    var sampleRateRatio = sampleRate / 16000;
    var newLength = Math.round(buffer.length / sampleRateRatio);
    var result = new Float32Array(newLength);
    var offsetResult = 0;
    var offsetBuffer = 0;
    while (offsetResult < result.length) {
      var nextOffsetBuffer = Math.round((offsetResult + 1) * sampleRateRatio);
      var accum = 0,
        count = 0;
      for (var i = offsetBuffer; i < nextOffsetBuffer && i < buffer.length; i++) {
        accum += buffer[i];
        count++;
      }
      result[offsetResult] = accum / count;
      offsetResult++;
      offsetBuffer = nextOffsetBuffer;
    }
    return result;
  }

            function getBuffer() {
                let buffers = [];
                for (let channel = 0; channel < numChannels; channel++) {
                    buffers.push(mergeBuffers(recBuffers[channel], recLength));
                }
                this.postMessage({command: 'getBuffer', data: buffers});
            }

            function clear() {
                recLength = 0;
                recBuffers = [];
                initBuffers();
            }

            function initBuffers() {
                for (let channel = 0; channel < numChannels; channel++) {
                    recBuffers[channel] = [];
                }
            }

            function mergeBuffers(recBuffers, recLength) {
                let result = new Float32Array(recLength);
                let offset = 0;
                for (let i = 0; i < recBuffers.length; i++) {
                    result.set(recBuffers[i], offset);
                    offset += recBuffers[i].length;
                }
                return result;
            }

            function interleave(inputL, inputR) {
                let length = inputL.length + inputR.length;
                let result = new Float32Array(length);

                let index = 0,
                    inputIndex = 0;

                while (index < length) {
                    result[index++] = inputL[inputIndex];
                    result[index++] = inputR[inputIndex];
                    inputIndex++;
                }
                return result;
            }

            function floatTo16BitPCM(output, offset, input) {
                for (let i = 0; i < input.length; i++, offset += 2) {
                    let s = Math.max(-1, Math.min(1, input[i]));
                    output.setInt16(offset, s < 0 ? s * 0x8000 : s * 0x7FFF, true);
                }
            }

            function writeString(view, offset, string) {
                for (let i = 0; i < string.length; i++) {
                    view.setUint8(offset + i, string.charCodeAt(i));
                }
            }

            function encodeWAV(samples) {
                let buffer = new ArrayBuffer(44 + samples.length * 2);
                let view = new DataView(buffer);

                /* RIFF identifier */
                writeString(view, 0, 'RIFF');
                /* RIFF chunk length */
                view.setUint32(4, 36 + samples.length * 2, true);
                /* RIFF type */
                writeString(view, 8, 'WAVE');
                /* format chunk identifier */
                writeString(view, 12, 'fmt ');
                /* format chunk length */
                view.setUint32(16, 16, true);
                /* sample format (raw) */
                view.setUint16(20, 1, true);
                /* channel count */
                view.setUint16(22, numChannels, true);
                /* sample rate */
                view.setUint32(24, sampleRate, true);
                /* byte rate (sample rate * block align) */
                view.setUint32(28, sampleRate * 4, true);
                /* block align (channel count * bytes per sample) */
                view.setUint16(32, numChannels * 2, true);
                /* bits per sample */
                view.setUint16(34, 16, true);
                /* data chunk identifier */
                writeString(view, 36, 'data');
                /* data chunk length */
                view.setUint32(40, samples.length * 2, true);

                floatTo16BitPCM(view, 44, samples);

                return view;
            }
        }, self);

        this.worker.postMessage({
            command: 'init',
            config: {
                sampleRate: this.context.sampleRate,
                numChannels: this.config.numChannels
            }
        });

        this.worker.onmessage = (e) => {
            let cb = this.callbacks[e.data.command].pop();
            if (typeof cb == 'function') {
                cb(e.data.data);
            }
        };
    }


    record() {
        this.recording = true;
    }

    stop() {
        this.recording = false;
    }

    clear() {
        this.worker.postMessage({command: 'clear'});
    }

    getBuffer(cb) {
        cb = cb || this.config.callback;
        if (!cb) throw new Error('Callback not set');

        this.callbacks.getBuffer.push(cb);

        this.worker.postMessage({command: 'getBuffer'});
    }

    exportWAV(cb, mimeType) {
        mimeType = mimeType || this.config.mimeType;
        cb = cb || this.config.callback;
        if (!cb) throw new Error('Callback not set');

        this.callbacks.exportWAV.push(cb);

        this.worker.postMessage({
            command: 'exportWAV',
            type: mimeType
        });
    }

    static
    forceDownload(blob, filename) {
        let url = (window.URL || window.webkitURL).createObjectURL(blob);
        let link = window.document.createElement('a');
        link.href = url;
        link.download = filename || 'output.wav';
        let click = document.createEvent("Event");
        click.initEvent("click", true, true);
        link.dispatchEvent(click);
    }
}

export default Recorder;

这是我从 github 存储库中获取的代码，但采样率为 48000

左右缓冲区下采样后的文件上传here

从我的组件类调用

 recorder && recorder.exportWAV(function(blob) {

            var formData=new FormData();

            formData.append("event_name",fileName);
            formData.append("file",new File([blob], fileName, {type: 'audio/mpeg;', lastModified: Date.now()}));
            formData.append("fileExtension", "mp3");
             fetch('http://localhost:6020/uploadFile', {
            method: "POST", // *GET, POST, PUT, DELETE, etc.
            cache: "no-cache", // *default, no-cache, reload, force-cache, only-if-cached

            redirect: "follow", // manual, *follow, error
            referrer: "no-referrer", // no-referrer, *client
            body: formData, // body data type must match "Content-Type" header
            })
            .then(response => response.json())
            .then(function(data){ console.log( JSON.stringify( data ) ) });

          },"audio/mp3");

【问题讨论】：

请建议在哪里调用它。 - 不清楚你在问什么。你可以在需要的地方调用它。 FWIW，您需要使用低通滤波器以避免重采样期间出现混叠。
创建一个minimal reproducible example。
@estus 我想提的一点是，由于我有两个通道，我应该传递什么，如何将它合并到一个缓冲区中，然后将其传递给下采样器？
这个问题不是很有建设性，因为你只是使用了别人的代码，它足够大，可以查看。如果您在使用第三方代码，则可能有一些库或示例可以更好地满足您的目的（我不能推荐一个）。我想你应该分别对左右通道进行下采样，除非 downsampleBuffer 被编写为支持多个通道 - 似乎它不是并且一次转换一个通道（缓冲区），正如它的名字所说的那样。
你可能会。或者您可以将其编码为 WAV，然后再编码为 MP3。这取决于您，您可以找到 MP3 编码的可能解决方案。同样，这超出了原始问题的范围（下采样）。

标签： javascript reactjs audio-recording downsampling

【解决方案1】：

我使用recorder.js 库成功地对我的音频剪辑（wav 文件）进行了下采样，并参考了this thread 中ilikerei 给出的解决方案。

在调用 encodeWav() 方法之前，将此方法添加到 recorder.js 以重新采样缓冲区以更改采样率。

function downsampleBuffer(buffer, rate) {
            if (rate == sampleRate) {
                return buffer;
            }
            if (rate > sampleRate) {
                throw "downsampling rate show be smaller than original sample rate";
            }
            var sampleRateRatio = sampleRate / rate;
            var newLength = Math.round(buffer.length / sampleRateRatio);
            var result = new Float32Array(newLength);
            var offsetResult = 0;
            var offsetBuffer = 0;
            while (offsetResult < result.length) {
                var nextOffsetBuffer = Math.round((offsetResult + 1) * sampleRateRatio);
                 // Use average value of skipped samples
                var accum = 0, count = 0;
                for (var i = offsetBuffer; i < nextOffsetBuffer && i < buffer.length; i++) {
                    accum += buffer[i];
                    count++;
                }
                result[offsetResult] = accum / count;
                // Or you can simply get rid of the skipped samples:
                // result[offsetResult] = buffer[nextOffsetBuffer];
                offsetResult++;
                offsetBuffer = nextOffsetBuffer;
            }
            return result;
        }

然后使用新的样本缓冲区调用 encodeWav。

var downsampledBuffer = downsampleBuffer(interleaved, targetRate);
var dataview = encodeWAV(downsampledBuffer);

现在使用新的采样率进行编码。

/* sample rate */
view.setUint32(24, newRate, true);
/* byte rate (sample rate * block align) */
view.setUint32(28, newRate * 4, true);

【讨论】：