java - 计算两个 channel 的音频电平/幅度/db

Question

我读过两篇关于从 AudioInputStream 中提取样本并将其转换为 dB 的文章。

https://stackoverflow.com/a/26576548/8428414

https://stackoverflow.com/a/26824664/8428414

据我了解 byte[] bytes; 的结构如下:

Index 0: Sample 0 (Left Channel)
Index 1: Sample 0 (Right Channel)
Index 2: Sample 1 (Left Channel)
Index 3: Sample 1 (Right Channel)
Index 4: Sample 2 (Left Channel)
Index 5: Sample 2 (Right Channel)

在第一篇文章中，它展示了如何从一个 channel (单声道)获取样本。

所以，我的问题是我想分别获取右声道和左声道的样本，以便计算左右声道的 dB。

这是代码。如何更改为分别获取左右声道？我无法理解索引 i 如何变化...

final byte[] buffer = new byte[2048];

float[] samples = new float[buffer.length / 2];

for (int n = 0; n != -1; n = in.read(buffer, 0, buffer.length)) {
    line.write(buffer, 0, n);

    for (int i = 0, sampleIndex = 0; i < n; ) {
        int sample = 0;

        sample |= buffer[i++] & 0xFF; // (reverse these two lines
        sample |= buffer[i++] << 8;   //  if the format is big endian)

        // normalize to range of +/-1.0f
        samples[sampleIndex++] = sample / 32768f;
    }

    float rms = 0f;
    for (float sample : samples) {
        rms += sample * sample;
    }

    rms = (float) Math.sqrt(rms / samples.length);

希望你能帮助我。预先感谢您。

Answer 1

立体声信号保存的格式称为interleaved 。也就是说，正如您所描述的正确，它是 LLRRLLRRLLRR...。因此，您首先需要读取左侧样本，然后读取右侧样本，依此类推。

我已经编辑了您的代码以反射(reflect)这一点。然而，通过refactoring还有一些改进的空间。 .

注意:代码更改仅处理交错。我还没有检查你的其余代码。

final byte[] buffer = new byte[2048];

// create two buffers. One for the left, one for the right channel.
float[] leftSamples = new float[buffer.length / 4];
float[] rightSamples = new float[buffer.length / 4];

for (int n = 0; n != -1; n = in.read(buffer, 0, buffer.length)) {
    line.write(buffer, 0, n);

    for (int i = 0, sampleIndex = 0; i < n; ) {
        int sample = 0;

        leftSample |= buffer[i++] & 0xFF; // (reverse these two lines
        leftSample |= buffer[i++] << 8;   //  if the format is big endian)

        rightSample |= buffer[i++] & 0xFF; // (reverse these two lines
        rightSample |= buffer[i++] << 8;   //  if the format is big endian)

        // normalize to range of +/-1.0f
        leftSamples[sampleIndex] = leftSample / 32768f;
        rightSamples[sampleIndex] = rightSample / 32768f;

        sampleIndex++;
    }

    // now compute RMS for left
    float leftRMS = 0f;
    for (float sample : leftSamples) {
        leftRMS += sample * sample;
    }

    leftRMS = (float) Math.sqrt(leftRMS / leftSamples.length);

    // ...and right
    float rightRMS = 0f;
    for (float sample : rightSamples) {
        rightRMS += sample * sample;
    }

    rightRMS = (float) Math.sqrt(rightRMS / rightSamples.length);
}