cooleshow/audio-analysis/src/main/java/com/yonge/Main.java

package com.yonge;

import be.tarsos.dsp.AudioDispatcher;
import be.tarsos.dsp.AudioEvent;
import be.tarsos.dsp.AudioProcessor;
import be.tarsos.dsp.io.jvm.JVMAudioInputStream;
import be.tarsos.dsp.mfcc.MFCC;
import be.tarsos.dsp.pitch.FastYin;
import be.tarsos.dsp.pitch.PitchDetectionHandler;
import be.tarsos.dsp.pitch.PitchDetectionResult;
import be.tarsos.dsp.pitch.PitchProcessor;
import com.yonge.audio.analysis.AudioFloatConverter;
import com.yonge.audio.analysis.detector.YINPitchDetector;
import com.yonge.audio.utils.ArrayUtil;
import com.yonge.netty.server.processor.WaveformWriter;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.ArrayUtils;

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.UnsupportedAudioFileException;
import java.io.*;
import java.net.URL;
import java.util.Arrays;
import java.util.Date;

/**
 * Description
 *
 * @author liujunchi
 * @date 2022-06-24
 */
public class Main {
    private final static int audioBufferSize = 2048;
    private final static int bufferOverlap = 1024;
    private final static int amountOfMelFilters = 20;
    private final static int amountOfCepstrumCoef = 30;
    private final static float lowerFilterFreq = 133.33f;
    private final static float upperFilterFreq = 8000f;

    private static AudioFormat audioFormat = new AudioFormat(44100, 16, 1, true, false);

    // private AudioFloatConverter converter = AudioFloatConverter.getConverter(audioFormat);

    public static void main(String[] args){
        try{
            float sampleRate = 44100;
            int audioBufferSize = 1024 *2;
            int bufferOverlap = 0;
            AudioFloatConverter converter = AudioFloatConverter.getConverter(audioFormat);
            //Create an AudioInputStream from my .wav file
            URL soundURL = Main.class.getResource("/WAV.wav");
            AudioInputStream stream = AudioSystem.getAudioInputStream(soundURL);
            // final MFCC mfccProcessor = new MFCC(audioBufferSize, stream.getFormat().getSampleRate(),
            //                                     amountOfCepstrumCoef, amountOfMelFilters, lowerFilterFreq, upperFilterFreq);

            FastYin detector = new FastYin(sampleRate, audioBufferSize *2);
            byte[] bytes = IOUtils.toByteArray(stream);
            AudioFormat format = stream.getFormat();

            int b = 0;
            int frequency = 0;
            File file = new File("D:\\project\\cooleshow\\audio-analysis\\target\\wav1.wav");

            WaveformWriter waveFileProcessor = new WaveformWriter(file.getAbsolutePath());
            byte[] bytes1 = new byte[0];
            // for (int i = 0; i < bytes.length; i++) {
            //     if (i%2 ==1) {
            //         System.out.println(bytes[i] + "----------" + bytes[i-1]);
            //     }
            // }
            while (bytes.length > audioBufferSize *2) {
                byte[] bufferData = ArrayUtil.extractByte(bytes, 0, audioBufferSize*2 - 1);

                bytes1 = ArrayUtil.mergeByte(bytes1, bufferData);
                byte[] bytes2 = new byte[bytes1.length *2];
                for (int i = 0; i < bytes1.length; i =i+2) {

                    bytes2[(i+1) *2]  = bytes2[i*2] = bytes1[i];
                    bytes2[(i+1) *2 +1] = bytes2[i*2 + 1] = bytes1[i +1];

                }
                // byte ff = bytes1[bytes1.length -1];
                // for (int start = 0, end = bytes1.length - 2; start < end; start++, end--) {
                //     byte temp = bytes1[end];
                //     bytes1[end] = bytes1[start];
                //     bytes1[start] = temp;
                // }
                // bytes1[bytes1.length -1] = ff;
                //
                // bytes1 = ArrayUtil.mergeByte(bufferData, bytes1);
                if (bytes2.length == audioBufferSize *4) {
                    waveFileProcessor.process(bytes2);


                    float[] sampleFloats = new float[audioBufferSize *2];

                    converter.toFloatArray(bytes2, sampleFloats);
                    int playFrequency = (int) detector.getPitch(sampleFloats).getPitch();
                    if (playFrequency != -1) {
                        System.out.println("play frequency is " + playFrequency);
                    }
                    bytes1 = new byte[0];
                }


                // YINPitchDetector frequencyDetector = new YINPitchDetector(sampleFloats.length, audioFormat.getSampleRate());
                //
                // playFrequency = (int) frequencyDetector.getFrequency(sampleFloats);
                //
                // System.out.println("frequencyDetector play frequency is " + playFrequency);
                // ArrayUtil.extractByte(channelContext.getChannelBufferBytes(), bufferSize, totalLength - 1)
                bytes  = ArrayUtil.extractByte(bytes, audioBufferSize, bytes.length - 1);
                // if (b == 1) {
                //     frequency += playFrequency;
                //     System.out.println("play frequency is " +frequency/2);
                //     b = 0;
                //     frequency = 0;
                // } else {
                //     frequency += playFrequency;
                //     b ++;
                // }
            }
            waveFileProcessor.processingFinished();


            //Convert into TarsosDSP API
            // JVMAudioInputStream audioStream = new JVMAudioInputStream(stream);
            // AudioDispatcher dispatcher = new AudioDispatcher(audioStream, audioBufferSize, bufferOverlap);
            // MyPitchDetector myPitchDetector = new MyPitchDetector();
            // dispatcher.addAudioProcessor(mfccProcessor);
            // dispatcher.addAudioProcessor(new AudioProcessor() {
            //     @Override
            //     public boolean process(AudioEvent audioEvent) {
            //         float[] mfccs = mfccProcessor.getMFCC();
            //
            //         // System.out.println(Arrays.toString(mfccs));
            //
            //         YINPitchDetector frequencyDetector = new YINPitchDetector(mfccs.length, sampleRate);
            //
            //         int playFrequency = (int)detector.getPitch(audioEvent.getFloatBuffer()).getPitch();
            //         // int playFrequency = (int) frequencyDetector.getFrequency(mfccs);
            //         System.out.println("play frequency is " +playFrequency);
            //         return true;
            //     }
            //
            //     @Override
            //     public void processingFinished() {
            //
            //     }
            // });
            // // dispatcher.addAudioProcessor(new MyPitchProcessor(PitchProcessor.PitchEstimationAlgorithm.FFT_YIN, sampleRate, audioBufferSize, myPitchDetector));
            // dispatcher.run();


        }
        catch(FileNotFoundException fne){fne.printStackTrace();}
        catch(UnsupportedAudioFileException uafe){uafe.printStackTrace();}
        catch(IOException ie){ie.printStackTrace();}
    }
}

class  MyPitchDetector implements PitchDetectionHandler {

    //Here the result of pitch is always less than half.
    @Override
    public void handlePitch(PitchDetectionResult pitchDetectionResult,
                            AudioEvent audioEvent) {
        if(pitchDetectionResult.getPitch() != -1){
            double timeStamp = audioEvent.getTimeStamp();
            float pitch = pitchDetectionResult.getPitch();
            float probability = pitchDetectionResult.getProbability();
            double rms = audioEvent.getRMS() * 100;
            String message = String.format("Pitch detected at %.2fs: %.2fHz ( %.2f probability, RMS: %.5f )\n", timeStamp,pitch,probability,rms);
            System.out.println(message);
        }
    }
}


class  MyPitchProcessor extends PitchProcessor {

    /**
     * Initialize a new pitch processor.
     *
     * @param algorithm  An enum defining the algorithm.
     * @param sampleRate The sample rate of the buffer (Hz).
     * @param bufferSize The size of the buffer in samples.
     * @param handler
     */
    public MyPitchProcessor(PitchEstimationAlgorithm algorithm, float sampleRate, int bufferSize, PitchDetectionHandler handler) {
        super(algorithm, sampleRate, bufferSize, handler);
    }


    @Override
    public boolean process(AudioEvent audioEvent) {
        return super.process(audioEvent);
    }
}