实时音频流 java

Live audio stream java

我正在实施从 MIC 到另一台 PC 上的 java 服务器的直播。但是我只听到白噪声。

我已经附加了客户端和服务器程序

Client:

import java.io.IOException;
import java.net.DatagramPacket;
import java.net.DatagramSocket;
import java.net.InetAddress;
import java.net.SocketException;
import java.net.UnknownHostException;

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.LineUnavailableException;
import javax.sound.sampled.TargetDataLine;

public class Mic 
{
    public byte[] buffer;
    private int port;
    static AudioInputStream ais;

    public static void main(String[] args)
    {
        TargetDataLine line;
        DatagramPacket dgp; 

        AudioFormat.Encoding encoding = AudioFormat.Encoding.PCM_SIGNED;
        float rate = 44100.0f;
        int channels = 2;
        int sampleSize = 16;
        boolean bigEndian = true;
        InetAddress addr;


        AudioFormat format = new AudioFormat(encoding, rate, sampleSize, channels, (sampleSize / 8) * channels, rate, bigEndian);

        DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);
        if (!AudioSystem.isLineSupported(info)) {
            System.out.println("Line matching " + info + " not supported.");
            return;
        }

        try
        {
            line = (TargetDataLine) AudioSystem.getLine(info);

            int buffsize = line.getBufferSize()/5;
            buffsize += 512; 

            line.open(format);

            line.start();   

            int numBytesRead;
            byte[] data = new byte[buffsize];

            addr = InetAddress.getByName("127.0.0.1");
            DatagramSocket socket = new DatagramSocket();
            while (true) {
                   // Read the next chunk of data from the TargetDataLine.
                   numBytesRead =  line.read(data, 0, data.length);
                   // Save this chunk of data.
                   dgp = new DatagramPacket (data,data.length,addr,50005);

                   socket.send(dgp);
                }

        }catch (LineUnavailableException e) {
            e.printStackTrace();
        }catch (UnknownHostException e) {
            // TODO: handle exception
        } catch (SocketException e) {
            // TODO: handle exception
        } catch (IOException e2) {
            // TODO: handle exception
        }
    }
}

并且服务器端没有问题。 运行 与 android 客户端 AudioRecord 完美搭配。

Server:

import java.io.ByteArrayInputStream;
import java.net.DatagramPacket;
import java.net.DatagramSocket;

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.SourceDataLine;

public class Server {

    AudioInputStream audioInputStream;
    static AudioInputStream ais;
    static AudioFormat format;
    static boolean status = true;
    static int port = 50005;
    static int sampleRate = 44100;

    static DataLine.Info dataLineInfo;
    static SourceDataLine sourceDataLine;

    public static void main(String args[]) throws Exception 
    {
        System.out.println("Server started at port:"+port);

        DatagramSocket serverSocket = new DatagramSocket(port);

        /**
         * Formula for lag = (byte_size/sample_rate)*2
         * Byte size 9728 will produce ~ 0.45 seconds of lag. Voice slightly broken.
         * Byte size 1400 will produce ~ 0.06 seconds of lag. Voice extremely broken.
         * Byte size 4000 will produce ~ 0.18 seconds of lag. Voice slightly more broken then 9728.
         */

        byte[] receiveData = new byte[4096];

        format = new AudioFormat(sampleRate, 16, 1, true, false);
        dataLineInfo = new DataLine.Info(SourceDataLine.class, format);
        sourceDataLine = (SourceDataLine) AudioSystem.getLine(dataLineInfo);
        sourceDataLine.open(format);
        sourceDataLine.start();

        //FloatControl volumeControl = (FloatControl) sourceDataLine.getControl(FloatControl.Type.MASTER_GAIN);
        //volumeControl.setValue(1.00f);

        DatagramPacket receivePacket = new DatagramPacket(receiveData, receiveData.length);

        ByteArrayInputStream baiss = new ByteArrayInputStream(receivePacket.getData());

        while (status == true) 
        {
            serverSocket.receive(receivePacket);
            ais = new AudioInputStream(baiss, format, receivePacket.getLength());
            toSpeaker(receivePacket.getData());
        }

        sourceDataLine.drain();
        sourceDataLine.close();
    }

    public static void toSpeaker(byte soundbytes[]) {
        try 
        {
            System.out.println("At the speaker");
            sourceDataLine.write(soundbytes, 0, soundbytes.length);
        } catch (Exception e) {
            System.out.println("Not working in speakers...");
            e.printStackTrace();
        }
    }
}

我建议您先将客户端录音机的音频写入文件。这将使您能够验证捕获的音频是否正常。您可以使用 sox 等实用程序将 PCM 转换为 WAV。

所以,我用正弦波(或某种模糊意义上类似于正弦波的东西)填充麦克风,您的程序运行良好。

我的具体改动是:

package audioclient;

import java.io.*;
import java.net.*;
import java.nio.ByteBuffer;

import javax.sound.sampled.*;

public class Mic {
    public byte[] buffer;
    private int port;
    static AudioInputStream ais;

        public static void main(String[] args) {
        TargetDataLine line;
        DatagramPacket dgp;

        AudioFormat.Encoding encoding = AudioFormat.Encoding.PCM_SIGNED;
        float rate = 44100.0f;
        int channels = 2;
        int sampleSize = 16;
        boolean bigEndian = true;
        InetAddress addr;

        AudioFormat format = new AudioFormat(encoding, rate, sampleSize, channels, (sampleSize / 8) * channels, rate, bigEndian);

        DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);
        if (!AudioSystem.isLineSupported(info)) {
            System.out.println("Line matching " + info + " not supported.");
            return;
        }

        try {
            line = (TargetDataLine) AudioSystem.getLine(info);

            //TOTALLY missed this.
            int buffsize = line.getBufferSize() / 5;
            buffsize += 512;

            line.open(format);

            line.start();

            int numBytesRead;
            byte[] data = new byte[buffsize];

            /*
             * MICK's injection: We have a buffsize of 512; it is best if the frequency
             * evenly fits into this (avoid skips, bumps, and pops). Additionally, 44100 Hz,
             * with two channels and two bytes per sample. That's four bytes; divide
             * 512 by it, you have 128.
             * 
             * 128 samples, 44100 per second; that's a minimum of 344 samples, or 172 Hz.
             * Well within hearing range; slight skip from the uneven division. Maybe
             * bump it up to 689 Hz.
             * 
             * That's a sine wave of shorts, repeated twice for two channels, with a
             * wavelength of 32 samples.
             * 
             * Note: Changed my mind, ignore specific numbers above.
             * 
             */
            {
                final int λ = 16;
                ByteBuffer buffer = ByteBuffer.allocate(λ * 2 * 8);
                for(int j = 0; j < 2; j++) {
                    for(double i = 0.0; i < λ; i++) {
                        System.out.println(j + " " + i);
                        //once for each sample
                        buffer.putShort((short)(Math.sin(Math.PI * (λ/i)) * Short.MAX_VALUE));
                        buffer.putShort((short)(Math.sin(Math.PI * (λ/i)) * Short.MAX_VALUE));
                    }
                }

                data = buffer.array();
            }

            addr = InetAddress.getByName("127.0.0.1");
            try(DatagramSocket socket = new DatagramSocket()) {
                while (true) {
                    for(byte b : data) System.out.print(b + " ");

                    // Read the next chunk of data from the TargetDataLine.
//                  numBytesRead = line.read(data, 0, data.length);

                    for(int i = 0; i < 64; i++) {
                        byte b = data[i];
                        System.out.print(b + " ");
                    }
                    System.out.println();

                    // Save this chunk of data.
                    dgp = new DatagramPacket(data, data.length, addr, 50005);    

                    for(int i = 0; i < 64; i++) {
                        byte b = dgp.getData()[i];
                        System.out.print(b + " ");
                    }
                    System.out.println();

                    socket.send(dgp);
                }
            }

        } catch (LineUnavailableException e) {
            e.printStackTrace();
        } catch (UnknownHostException e) {
            // TODO: handle exception
        } catch (SocketException e) {
            // TODO: handle exception
        } catch (IOException e2) {
            // TODO: handle exception
        }
    }
}

显然我将它误解为一个 512 字节长的片段并弄乱了正弦波,但事实是,它产生了它本来应该发出的声音——在特定的音调上发出令人头脑麻木的嘎嘎声。

考虑到这一点,我不怀疑问题出在您的代码中。我要检查的第一件事是您的系统正在为音频窃听哪条线路。您连接了多个麦克风吗?也许是网络摄像头麦克风?您可以使用 PulseAudio Volume Control 等实用程序进行检查。如果您还没有检查过麦克风的功能,您也可以这样做;他们确实有寿命。

加扰音频流中的位并不少见,也不难;但我看不到任何地方可以这样做。

一个想法可能是修改您的程序以尝试在本地播放声音,然后再将其发送到服务器。这样,您至少可以确定问题是前置还是 post-Mic.

当客户端和服务器使用不同大小的数据缓冲区时,其中一个将被截断,并可能导致一个或两个产生伪影。

您的服务器缓冲区大小设置为 byte[] receiveData = new byte[4096];

您的客户端缓冲区大小出于某种原因是动态的,并设置为 byte[] data = new byte[buffsize];

将客户端缓冲区大小设置为静态 4096 以匹配服务器:byte[] data = new byte[4096];

或者只要确保它们的大小相同...

在客户端和服务器上匹配音频格式很重要,例如将 Client.java 中的格式更改为:format = new AudioFormat(sampleRate, 16, 1, true, false); 您还需要在两个程序上使用相同的缓冲区大小。

所以这是一个老问题,但解决这个问题对我有所帮助,我想我的发现可能会对其他人有所帮助,所以..这就是我解决你描述的问题的方法:

在我的机器上,正在更改

boolean bigEndian = true;

boolean bigEndian = false;

解决了白噪声问题(显然是字节顺序问题)

如果这是您所做的唯一更改,生成的音频将具有低音调,这是因为在 Mic 侧您收集 2 个通道而在 Speaker 侧您通过一个通道播放.

要解决这个问题,只需更改此行:

format = new AudioFormat(sampleRate, 16, 1, true, false);

format = new AudioFormat(sampleRate, 16, 2, true, false);

然后音频应该清晰易懂