Decoding audio via Android using FFMpeg

2019-03-10 11:50发布

站内文章 / Android
16 0 0

问题:

I can play Wav files using the below code without issues. When trying to play the exact same media in Mp3 format I only get garbled junk. I believe I am fundamentally misunderstanding how the avcodec_decode_audio3 function works.

Since the Wav file contains PCM data when it is decoded it can go straight to the AudioTrack.write function. There must be some additional step to get Mp3s to work like this. I don't know what I'm missing, but I've been pulling my hair out for a week now.

Java Code

package com.rohaupt.RRD2;

import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;

import android.app.Activity;
import android.media.AudioFormat;
import android.media.AudioManager;
import android.media.AudioTrack;
import android.media.MediaPlayer;
import android.os.Bundle;
import android.os.SystemClock;

public class player extends Activity
{
    private AudioTrack track;
    private FileOutputStream os;
    /** Called when the activity is first created. */
    @Override
    public void onCreate(Bundle savedInstanceState)
    {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.main);
        createEngine();

        MediaPlayer mp = new MediaPlayer();
        mp.start();

        int bufSize = AudioTrack.getMinBufferSize(32000,
                                                  AudioFormat.CHANNEL_CONFIGURATION_STEREO, 
                                                  AudioFormat.ENCODING_PCM_16BIT);


        track = new AudioTrack(AudioManager.STREAM_MUSIC, 
                               32000, 
                               AudioFormat.CHANNEL_CONFIGURATION_STEREO, 
                               AudioFormat.ENCODING_PCM_16BIT, 
                               bufSize,
                               AudioTrack.MODE_STREAM);

        byte[] bytes = new byte[bufSize];

        try {
            os = new FileOutputStream("/sdcard/a.out",false);
        } catch (FileNotFoundException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

        String result = loadFile("/sdcard/a.mp3",bytes);

        try {
            os.close();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    void playSound(byte[] buf, int size) {  
        //android.util.Log.v("ROHAUPT", "RAH Playing");
        if(track.getPlayState()!=AudioTrack.PLAYSTATE_PLAYING)
            track.play();
        track.write(buf, 0, size);

        try {
            os.write(buf,0,size);
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }


    private native void createEngine();
    private native String loadFile(String file, byte[] array);

    /** Load jni .so on initialization*/ 
    static {
         System.loadLibrary("avutil"); 
         System.loadLibrary("avcore"); 
         System.loadLibrary("avcodec");
         System.loadLibrary("avformat");
         System.loadLibrary("avdevice");
         System.loadLibrary("swscale");
         System.loadLibrary("avfilter");
         System.loadLibrary("ffmpeg");
    }
}

C Code

#include <assert.h>
#include <jni.h>
#include <string.h>
#include <android/log.h>

#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"

#define DEBUG_TAG "ROHAUPT"  

void Java_com_rohaupt_RRD2_player_createEngine(JNIEnv* env, jclass clazz)
    {
        avcodec_init();

        av_register_all();


    }

    jstring Java_com_rohaupt_RRD2_player_loadFile(JNIEnv* env, jobject obj,jstring file,jbyteArray array)
    {   
        jboolean            isCopy;  
        int                 i;
        int                 audioStream=-1;
        int                 res;
        int                 decoded = 0;
        int                 out_size;
        AVFormatContext     *pFormatCtx;
        AVCodecContext      *aCodecCtx;
        AVCodecContext      *c= NULL;
        AVCodec             *aCodec;
        AVPacket            packet;
        jclass              cls = (*env)->GetObjectClass(env, obj);
        jmethodID           play = (*env)->GetMethodID(env, cls, "playSound", "([BI)V");//At the begining of your main function
        const char *        szfile = (*env)->GetStringUTFChars(env, file, &isCopy);
        int16_t *           pAudioBuffer = (int16_t *) av_malloc (AVCODEC_MAX_AUDIO_FRAME_SIZE*2+FF_INPUT_BUFFER_PADDING_SIZE);
        int16_t *           outBuffer = (int16_t *) av_malloc (AVCODEC_MAX_AUDIO_FRAME_SIZE*2+FF_INPUT_BUFFER_PADDING_SIZE);


        __android_log_print(ANDROID_LOG_INFO, DEBUG_TAG, "RAH28 Starting");
        res = av_open_input_file(&pFormatCtx, szfile, NULL, 0, NULL);
        if(res!=0)
        {
            __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH opening input failed with result: [%d]", res);
            return file;
        }

        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH getting stream info");
        res = av_find_stream_info(pFormatCtx);
        if(res<0)
        {
            __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH getting stream info failed with result: [%d]", res);
            return file;
        }

        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH getting audio stream");
        for(i=0; i < pFormatCtx->nb_streams; i++) {
          if(pFormatCtx->streams[i]->codec->codec_type==AVMEDIA_TYPE_AUDIO &&
             audioStream < 0) {
            audioStream=i;
          }
        }


        if(audioStream==-1)
        {
            __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH couldn't find audio stream");
            return file;
        }
        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH audio stream found with result: [%d]", res);


        aCodecCtx=pFormatCtx->streams[audioStream]->codec;
        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH audio codec info loaded");

        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH audio codec info [%d]", aCodecCtx->codec_id);

        aCodec = avcodec_find_decoder(aCodecCtx->codec_id);
        if(!aCodec) {
           __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH audio codec unsupported");
           return file;
        }
        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH audio codec info found");


        res = avcodec_open(aCodecCtx, aCodec);
        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH audio codec loaded [%d] [%d]",aCodecCtx->sample_fmt,res);

        //c=avcodec_alloc_context();
        av_init_packet(&packet);


        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH channels [%d] sample rate [%d] sample format [%d]",aCodecCtx->channels,aCodecCtx->sample_rate,aCodecCtx->sample_fmt);


        int x,y;
        x=0;y=0;
        while (av_read_frame(pFormatCtx, &packet)>= 0) {
            __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH frame read: [%d] [%d]",x++,y);

            if (aCodecCtx->codec_type == AVMEDIA_TYPE_AUDIO) {
                        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH audio ready");
                        int data_size = AVCODEC_MAX_AUDIO_FRAME_SIZE*2+FF_INPUT_BUFFER_PADDING_SIZE;
                        int size=packet.size;
                        y=0;
                        decoded = 0;
                        __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH packet size: [%d]", size);
                        while(size > 0) {

                                __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH decoding: [%d] [%d]",x,y++);
                                int len = avcodec_decode_audio3(aCodecCtx, pAudioBuffer, &data_size, &packet);



                                __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH 1 size [%d] len [%d] data_size [%d] out_size [%d]",size,len,data_size,out_size);
                                jbyte *bytes = (*env)->GetByteArrayElements(env, array, NULL);

                                memcpy(bytes + decoded, pAudioBuffer, len); //


                                __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH 2");

                                (*env)->ReleaseByteArrayElements(env, array, bytes, 0);
                                __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH 3");

                                (*env)->CallVoidMethod(env, obj, play, array, len);

                                __android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH 4");


                                size -= len;
                                decoded += len;

                       }
                       av_free_packet(&packet);
            }

     }

          // Close the video file
        av_close_input_file(pFormatCtx);

        //__android_log_print(ANDROID_LOG_DEBUG, DEBUG_TAG, "RAH Finished Running result: [%d]", res);
        (*env)->ReleaseStringUTFChars(env, file, szfile);   
        return file;  
    }

To add some detail. When Calling this function with a Wav File I get the following Log Data

I/ROHAUPT (  227): RAH28 Starting
D/ROHAUPT (  227): RAH getting stream info
D/ROHAUPT (  227): RAH getting audio stream
D/ROHAUPT (  227): RAH audio stream found with result: [0]
D/ROHAUPT (  227): RAH audio codec info loaded
D/ROHAUPT (  227): RAH audio codec info [65536]
D/ROHAUPT (  227): RAH audio codec info found
D/ROHAUPT (  227): RAH audio codec loaded [1] [0]
D/ROHAUPT (  227): RAH channels [2] sample rate [32000] sample format [1]
D/ROHAUPT (  227): RAH frame read: [0] [0]
D/ROHAUPT (  227): RAH audio ready
D/ROHAUPT (  227): RAH packet size: [4096]
D/ROHAUPT (  227): RAH decoding: [1] [0]
D/ROHAUPT (  227): RAH 1 size [4096] len [4096] data_size [4096] out_size [0]
D/ROHAUPT (  227): RAH 2
D/ROHAUPT (  227): RAH 3
D/ROHAUPT (  227): RAH 4
D/ROHAUPT (  227): RAH frame read: [1] [1]
D/ROHAUPT (  227): RAH audio ready
...
D/ROHAUPT (  227): RAH frame read: [924] [1]
D/ROHAUPT (  227): RAH audio ready
D/ROHAUPT (  227): RAH packet size: [4096]
D/ROHAUPT (  227): RAH decoding: [925] [0]
D/ROHAUPT (  227): RAH 1 size [4096] len [4096] data_size [4096] out_size [0]
D/ROHAUPT (  227): RAH 2
D/ROHAUPT (  227): RAH 3
D/ROHAUPT (  227): RAH 4
D/ROHAUPT (  227): RAH frame read: [925] [1]
D/ROHAUPT (  227): RAH audio ready
D/ROHAUPT (  227): RAH packet size: [3584]
D/ROHAUPT (  227): RAH decoding: [926] [0]
D/ROHAUPT (  227): RAH 1 size [3584] len [3584] data_size [3584] out_size [0]
D/ROHAUPT (  227): RAH 2
D/ROHAUPT (  227): RAH 3
D/ROHAUPT (  227): RAH 4

When calling with an Mp3 file I get the following

I/ROHAUPT (  280): RAH28 Starting
D/ROHAUPT (  280): RAH getting stream info
D/ROHAUPT (  280): RAH getting audio stream
D/ROHAUPT (  280): RAH audio stream found with result: [0]
D/ROHAUPT (  280): RAH audio codec info loaded
D/ROHAUPT (  280): RAH audio codec info [86017]
D/ROHAUPT (  280): RAH audio codec info found
D/ROHAUPT (  280): RAH audio codec loaded [1] [0]
D/ROHAUPT (  280): RAH channels [2] sample rate [32000] sample format [1]
D/ROHAUPT (  280): RAH frame read: [0] [0]
D/ROHAUPT (  280): RAH audio ready
D/ROHAUPT (  280): RAH packet size: [432]
D/ROHAUPT (  280): RAH decoding: [1] [0]
D/ROHAUPT (  280): RAH 1 size [432] len [432] data_size [4608] out_size [0]
D/ROHAUPT (  280): RAH 2
...
D/ROHAUPT (  280): RAH frame read: [822] [1]
D/ROHAUPT (  280): RAH audio ready
D/ROHAUPT (  280): RAH packet size: [432]
D/ROHAUPT (  280): RAH decoding: [823] [0]
D/ROHAUPT (  280): RAH 1 size [432] len [432] data_size [4608] out_size [0]
D/ROHAUPT (  280): RAH 2
D/ROHAUPT (  280): RAH 3
D/ROHAUPT (  280): RAH 4
D/ROHAUPT (  280): RAH frame read: [823] [1]
D/ROHAUPT (  280): RAH audio ready
D/ROHAUPT (  280): RAH packet size: [432]
D/ROHAUPT (  280): RAH decoding: [824] [0]
D/ROHAUPT (  280): RAH 1 size [432] len [432] data_size [4608] out_size [0]
D/ROHAUPT (  280): RAH 2
D/ROHAUPT (  280): RAH 3
D/ROHAUPT (  280): RAH 4

回答1:

I was able to solve my problem by taking the audio_decode_example code found in the api_example.c file in libavcodec of the ffmpeg source and modify it to suit my needs. Below is the code. Just to note, it doesn't dynamically pick the correct codec to decode with, that is something I'll have to fix next along with a few other items. The java code remains untouched.

void Java_com_rohaupt_RRD2_player_Example(JNIEnv* env, jobject obj,jstring file,jbyteArray array)
    {
        jboolean            isfilenameCopy;
        const char *        filename = (*env)->GetStringUTFChars(env, file, &isfilenameCopy);
        AVCodec *codec;
        AVCodecContext *c= NULL;
        int out_size, len;
        FILE *f, *outfile;
        uint8_t *outbuf;
        uint8_t inbuf[AUDIO_INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
        AVPacket avpkt;
        jclass              cls = (*env)->GetObjectClass(env, obj);
        jmethodID           play = (*env)->GetMethodID(env, cls, "playSound", "([BI)V");//At the begining of your main function

        av_init_packet(&avpkt);

        printf("Audio decoding\n");

        /* find the mpeg audio decoder */
        codec = avcodec_find_decoder(CODEC_ID_MP3);
        if (!codec) {
            fprintf(stderr, "codec not found\n");
            exit(1);
        }

        c= avcodec_alloc_context();

        /* open it */
        if (avcodec_open(c, codec) < 0) {
            fprintf(stderr, "could not open codec\n");
            exit(1);
        }

        outbuf = malloc(AVCODEC_MAX_AUDIO_FRAME_SIZE);

        f = fopen(filename, "rb");
        if (!f) {
            fprintf(stderr, "could not open %s\n", filename);
            exit(1);
        }

        /* decode until eof */
        avpkt.data = inbuf;
        avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);

        while (avpkt.size > 0) {
            out_size = AVCODEC_MAX_AUDIO_FRAME_SIZE;
            len = avcodec_decode_audio3(c, (short *)outbuf, &out_size, &avpkt);
            if (len < 0) {
                fprintf(stderr, "Error while decoding\n");
                exit(1);
            }
            if (out_size > 0) {
                /* if a frame has been decoded, output it */
                jbyte *bytes = (*env)->GetByteArrayElements(env, array, NULL);
                memcpy(bytes, outbuf, out_size); //
                (*env)->ReleaseByteArrayElements(env, array, bytes, 0);
                (*env)->CallVoidMethod(env, obj, play, array, out_size);

            }
            avpkt.size -= len;
            avpkt.data += len;
            if (avpkt.size < AUDIO_REFILL_THRESH) {
                /* Refill the input buffer, to avoid trying to decode
                 * incomplete frames. Instead of this, one could also use
                 * a parser, or use a proper container format through
                 * libavformat. */
                memmove(inbuf, avpkt.data, avpkt.size);
                avpkt.data = inbuf;
                len = fread(avpkt.data + avpkt.size, 1,
                            AUDIO_INBUF_SIZE - avpkt.size, f);
                if (len > 0)
                    avpkt.size += len;
            }
        }

        fclose(f);
        free(outbuf);

        avcodec_close(c);
        av_free(c);
    }


回答2:

Ah, you might need to check the data_size value after the call to avcodec_decode_audio3: right now you always feed the return value to the play method, but if data_size is less than 0 then it is not a valid frame decode.



标签： android audio ffmpeg android-ndk
举报

收藏的人(0)

Ta的文章 更多文章
登录 后发表评论
0条评论
还没有人评论过~