(原创)speex与wav格式音频文件的互相转换(二)

之前写过了如何将speex与wav格式的音频互相转换，如果没有看过的请看一下连接

http://www.cnblogs.com/dongweiq/p/4515186.html

虽然自己实现了相关的压缩算法，但是发现还是与gauss的压缩比例差了一些，一部分是参数设置的问题，另外一部分是没有使用ogg的问题。

本来想研究一下gauss的ogg算法，然后将他录制的音频转为wav格式，再继续进行后面的频谱绘制之类的。

在后续的研究gauss的解码过程，他是先解了ogg的格式，然后分段，然后去掉speex的头，然后把一段段的speex数据再解码成pcm的原数据，最后使用audiotrack一段段播放出来了。audiotrack播放的时候是阻塞的，所以播了多久就解了多久。

既然他得到了一段段pcm的原数据，那我就可以去将这一段段的原数据拼起来，最后得到解码完成的整个的pcm数据，最后加上wav的头不就可以直接转换成wav格式的音频了么？？？

前天的时候想到这里，立马就去改了。

SpeexDecoder是gauss的demo里主要的解码类，我们复制一份，改名为SpeexFileDecoder

去掉里面跟播放相关的audiotrack变量，因为我们要得到的是解码数据，跟播放无关。

修改后代码如下

package com.sixin.speex;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.RandomAccessFile;
import java.util.ArrayList;
import java.util.List;

import android.media.AudioFormat;
import android.media.AudioManager;
import android.media.AudioTrack;
import android.os.RecoverySystem.ProgressListener;
import android.util.Log;

/**
 * 采用Jspeex方案，首先解包，从ogg里面接出来，然后使用speex decode将speex转为wav数据并进行播放
 * 
 * @author Honghe
 */
public class SpeexFileDecoder {

    protected Speex speexDecoder;
    private String errmsg = null;
    private List<ProgressListener> listenerList = new ArrayList<ProgressListener>();
    private File srcPath;
    private File dstPath;

    public SpeexFileDecoder(File srcPath, File dstPath) throws Exception {
        this.srcPath = srcPath;
        this.dstPath = dstPath;
    }

    private void initializeAndroidAudio(int sampleRate) throws Exception {
        int minBufferSize = AudioTrack.getMinBufferSize(sampleRate, AudioFormat.CHANNEL_OUT_MONO, AudioFormat.ENCODING_PCM_16BIT);

        if (minBufferSize < 0) {
            throw new Exception("Failed to get minimum buffer size: " + Integer.toString(minBufferSize));
        }
    }

    public void addOnMetadataListener(ProgressListener l) {
        listenerList.add(l);
    }

    public String getErrmsg() {
        return errmsg;
    }

    public void decode() throws Exception {
        errmsg = null;
        byte[] header = new byte[2048];
        byte[] payload = new byte[65536];
        final int OGG_HEADERSIZE = 27;
        final int OGG_SEGOFFSET = 26;
        final String OGGID = "OggS";
        int segments = 0;
        int curseg = 0;
        int bodybytes = 0;
        int decsize = 0;
        int packetNo = 0;
        // construct a new decoder
        speexDecoder = new Speex();
        speexDecoder.init();
        // open the input stream
        RandomAccessFile dis = new RandomAccessFile(srcPath, "r");
        FileOutputStream fos = new FileOutputStream(dstPath);

        int origchksum;
        int chksum;
        try {

            // read until we get to EOF
            while (true) {
                if (Thread.interrupted()) {
                    dis.close();
                    return;
                }

                // read the OGG header
                dis.readFully(header, 0, OGG_HEADERSIZE);
                origchksum = readInt(header, 22);
                readLong(header, 6);
                header[22] = 0;
                header[23] = 0;
                header[24] = 0;
                header[25] = 0;
                chksum = OggCrc.checksum(0, header, 0, OGG_HEADERSIZE);

                // make sure its a OGG header
                if (!OGGID.equals(new String(header, 0, 4))) {
                    System.err.println("missing ogg id!");
                    errmsg = "missing ogg id!";
                    return;
                }

                /* how many segments are there? */
                segments = header[OGG_SEGOFFSET] & 0xFF;
                dis.readFully(header, OGG_HEADERSIZE, segments);
                chksum = OggCrc.checksum(chksum, header, OGG_HEADERSIZE, segments);

                /* decode each segment, writing output to wav */
                for (curseg = 0; curseg < segments; curseg++) {

                    if (Thread.interrupted()) {
                        dis.close();
                        return;
                    }

                    /* get the number of bytes in the segment */
                    bodybytes = header[OGG_HEADERSIZE + curseg] & 0xFF;
                    if (bodybytes == 255) {
                        System.err.println("sorry, don't handle 255 sizes!");
                        return;
                    }
                    dis.readFully(payload, 0, bodybytes);
                    chksum = OggCrc.checksum(chksum, payload, 0, bodybytes);

                    /* decode the segment */
                    /* if first packet, read the Speex header */
                    if (packetNo == 0) {
                        if (readSpeexHeader(payload, 0, bodybytes, true)) {

                            packetNo++;
                        } else {
                            packetNo = 0;
                        }
                    } else if (packetNo == 1) { // Ogg Comment packet
                        packetNo++;
                    } else {

                        /* get the amount of decoded data */
                        short[] decoded = new short[160];
                        if ((decsize = speexDecoder.decode(payload, decoded, 160)) > 0) {
                            //把边解边播改为写文件
                            fos.write(ShortAndByte.shortArray2ByteArray(decoded), 0, decsize * 2);
                        }
                        packetNo++;
                    }
                }
                if (chksum != origchksum)
                    throw new IOException("Ogg CheckSums do not match");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        fos.close();
        dis.close();
    }

    /**
     * Reads the header packet.
     * 
     * <pre>
     *  0 -  7: speex_string: "Speex   "
     *  8 - 27: speex_version: "speex-1.0"
     * 28 - 31: speex_version_id: 1
     * 32 - 35: header_size: 80
     * 36 - 39: rate
     * 40 - 43: mode: 0=narrowband, 1=wb, 2=uwb
     * 44 - 47: mode_bitstream_version: 4
     * 48 - 51: nb_channels
     * 52 - 55: bitrate: -1
     * 56 - 59: frame_size: 160
     * 60 - 63: vbr
     * 64 - 67: frames_per_packet
     * 68 - 71: extra_headers: 0
     * 72 - 75: reserved1
     * 76 - 79: reserved2
     * </pre>
     * 
     * @param packet
     * @param offset
     * @param bytes
     * @return
     * @throws Exception
     */
    private boolean readSpeexHeader(final byte[] packet, final int offset, final int bytes, boolean init) throws Exception {
        if (bytes != 80) {
            return false;
        }
        if (!"Speex   ".equals(new String(packet, offset, 8))) {
            return false;
        }
        //        int mode = packet[40 + offset] & 0xFF;
        int sampleRate = readInt(packet, offset + 36);
        //        int channels = readInt(packet, offset + 48);
        //        int nframes = readInt(packet, offset + 64);
        //        int frameSize = readInt(packet, offset + 56);
        //        RongXinLog.SystemOut("mode=" + mode + " sampleRate==" + sampleRate + " channels=" + channels
        //                + "nframes=" + nframes + "framesize=" + frameSize);
        initializeAndroidAudio(sampleRate);

        if (init) {
            // return speexDecoder.init(mode, sampleRate, channels, enhanced);
            return true;
        } else {
            return true;
        }
    }

    protected static int readInt(final byte[] data, final int offset) {
        /*
         * no 0xff on the last one to keep the sign
         */
        return (data[offset] & 0xff) | ((data[offset + 1] & 0xff) << 8) | ((data[offset + 2] & 0xff) << 16) | (data[offset + 3] << 24);
    }

    protected static long readLong(final byte[] data, final int offset) {
        /*
         * no 0xff on the last one to keep the sign
         */
        return (data[offset] & 0xff) | ((data[offset + 1] & 0xff) << 8) | ((data[offset + 2] & 0xff) << 16) | ((data[offset + 3] & 0xff) << 24) | ((data[offset + 4] & 0xff) << 32)
                | ((data[offset + 5] & 0xff) << 40) | ((data[offset + 6] & 0xff) << 48) | (data[offset + 7] << 56);
    }

    protected static int readShort(final byte[] data, final int offset) {
        /*
         * no 0xff on the last one to keep the sign
         */
        return (data[offset] & 0xff) | (data[offset + 1] << 8);
    }

}

注意上面因为speex解码出来的是160个short类型的数组，而java写文件要求写入的是byte数组，所以我们还是用到了short转byte数组的方法shortArray2ByteArray，我封装了一个类。也贴在下边

package com.sixin.speex;

public class ShortAndByte {
    /** 
    * @功能 短整型与字节的转换 
    * @param 短整型 
    * @return 两位的字节数组 
    */
    public static byte[] shortToByte(short number) {
        int temp = number;
        byte[] b = new byte[2];
        for (int i = 0; i < b.length; i++) {
            b[i] = new Integer(temp & 0xff).byteValue();// 将最低位保存在最低位  
            temp = temp >> 8; // 向右移8位  
        }
        return b;
    }

    /** 
     * @功能 字节的转换与短整型 
     * @param 两位的字节数组 
     * @return 短整型 
     */
    public static short byteToShort(byte[] b) {
        short s = 0;
        short s0 = (short) (b[0] & 0xff);// 最低位  
        short s1 = (short) (b[1] & 0xff);
        s1 <<= 8;
        s = (short) (s0 | s1);
        return s;
    }

    /** 
     * @说明 主要是为解析静态数据包，将一个字节数组转换为short数组 
     * @param b 
     */
    public static short[] byteArray2ShortArray(byte[] b) {
        int len = b.length / 2;
        int index = 0;
        short[] re = new short[len];
        byte[] buf = new byte[2];
        for (int i = 0; i < b.length;) {
            buf[0] = b[i];
            buf[1] = b[i + 1];
            short st = byteToShort(buf);
            re[index] = st;
            index++;
            i += 2;
        }
        return re;
    }

    /** 
     * @说明 主要是为解析静态数据包，将一个short数组反转为字节数组 
     * @param b 
     */
    public static byte[] shortArray2ByteArray(short[] b) {
        byte[] rebt = new byte[b.length * 2];
        int index = 0;
        for (int i = 0; i < b.length; i++) {
            short st = b[i];
            byte[] bt = shortToByte(st);
            rebt[index] = bt[0];
            rebt[index + 1] = bt[1];
            index += 2;
        }
        return rebt;
    }
}

读出来的原数据我们放入到了dstPath的文件，再来看看是怎么操作的呢？其中我还是修改了gauss的speexplayer方法。

我们复制speexPlayer方法，改名为SpeexFileDecoderHelper，按照如下方法修改

/**
 * 
 */
package com.sixin.speex;

import java.io.File;

import android.os.Handler;

/**
 * @author honghe
 * 
 */
public class SpeexFileDecoderHelper {
    private String srcName = null;
    private String dstName = null;
    private SpeexFileDecoder speexdec = null;
    private OnSpeexFileCompletionListener speexListener = null;
    private static final int speexdecode_completion = 1001;
    private static final int speexdecode_error = 1002;

    public Handler handler = new Handler() {
        public void handleMessage(android.os.Message msg) {
            int what = msg.what;
            switch (what) {
            case speexdecode_completion:
                if (speexListener != null) {
                    speexListener.onCompletion(speexdec);
                } else {
                    System.out.println("司信---------null===speexListener");
                }
                break;
            case speexdecode_error:
                if (speexListener != null) {
                    File file = new File(SpeexFileDecoderHelper.this.srcName);
                    if (null != file && file.exists()) {
                        file.delete();
                    }
                    speexListener.onError(null);
                }
                break;
            default:
                break;
            }
        };
    };

    public SpeexFileDecoderHelper(String fileName,String dstName, OnSpeexFileCompletionListener splistener) {
        this.speexListener = splistener;
        this.srcName = fileName;
        this.dstName = dstName;
        try {
            speexdec = new SpeexFileDecoder(new File(this.srcName),new File(this.dstName));
        } catch (Exception e) {
            e.printStackTrace();
            File file = new File(SpeexFileDecoderHelper.this.srcName);
            if (null != file && file.exists()) {
                file.delete();
            }
        }
    }

    public void startDecode() {
        RecordDecodeThread rpt = new RecordDecodeThread();
        Thread th = new Thread(rpt);
        th.start();
    }

    public boolean isDecoding = false;

    class RecordDecodeThread extends Thread {

        public void run() {
            try {
                if (speexdec != null) {
                    isDecoding = true;
                    speexdec.decode();
                    if (null != speexdec.getErrmsg()) {
                        throw new Exception(speexdec.getErrmsg());
                    }
                }
                System.out.println("RecordPlayThread   文件转换完成");
                if (isDecoding) {
                    handler.sendEmptyMessage(speexdecode_completion);
                } 
                isDecoding = false;
            } catch (Exception t) {
                t.printStackTrace();
                System.out.println("RecordPlayThread   文件转换出错");
                handler.sendEmptyMessage(speexdecode_error);
                isDecoding = false;
            }
        }
    }

    /**
     * 结束播放
     */
    public void stopDecode() {
        isDecoding = false;
    }

    public String getSpxFileName() {
        return this.srcName;
    };
}

这个方法是开启了一个现成去解码，然后解码完成后会发送handler，调用回调方法，通知解码失败还是成功。OnSpeexFileCompletionListener这个很简单，我需要贴吗？还是贴上吧，省的被骂娘。

package com.sixin.speex;

/**
 * Speex音频解码完成监听
 * @author honghe
 *
 */
public interface OnSpeexFileCompletionListener {
    void onCompletion(SpeexFileDecoder speexdecoder);
    void onError(Exception ex);
}

到此代码都贴出来了。什么？！还不会用？哦，我还没写怎么加wav头呢，那再写个方法吧

/**
     * 语音转换
     * 
     * @param name
     * @param srcFileName spx文件名
     * @param dstFileName 转换后得到文件的文件名
     */
    public static void decodeSpx(Context context, String srcFileName, final String dstFileName) {
        final String temppath = AudioFileFunc.getFilePathByName("temp.raw");
        try {
            // 如果是speex录音
            if (srcFileName != null && srcFileName.endsWith(".spx")) {
                if (mSpeexFileDecoderHelper != null && mSpeexFileDecoderHelper.isDecoding) {
                    stopMusic(context);
                } else {
                    muteAudioFocus(context, true);
                    mSpeexFileDecoderHelper = new SpeexFileDecoderHelper(srcFileName, temppath, new OnSpeexFileCompletionListener() {

                        @Override
                        public void onError(Exception ex) {
                            System.out.println("转换错误");
                        }

                        @Override
                        public void onCompletion(SpeexFileDecoder speexdecoder) {
                            System.out.println("转换完成");
                            WaveJoin.copyWaveFile(temppath, dstFileName);
                        }
                    });
                    mSpeexFileDecoderHelper.startDecode();
                }
            } else {
                System.out.println("音频文件格式不正确");
            }

        } catch (Exception e) {
            e.printStackTrace();
        }
    }

copyWaveFile这个方法在哪里？去看开头的那个链接吧，上面有。不过在加wav头的时候要注意，加的头要和你录制音频的时候设置的参数一致，比如samplerate，声道数，framesize这些，我就设置错了一次，gauss录制音频的时候使用的是单声道，我加入的wav头的channel设置成了2，结果放出来的声音老搞笑了，就跟快放一样。有兴趣你可以试试。

代码已更新

代码链接如下：

https://github.com/dongweiq/study/tree/master/Record

我的github地址：https://github.com/dongweiq/study

欢迎关注，欢迎star o(∩_∩)o 。有什么问题请邮箱联系 dongweiqmail@gmail.com qq714094450