我正在尝试将音频文件解码为PCM以与AudioTrack配合使用。音频是吱吱作响的，吵闹的，只是简单的乱码，随意的第二声听起来应该是，但主要是完全混乱。我不确定我的错误在哪里，是否将数组传递回playSound？
提前谢谢你，我真的很感谢这件事的帮助，因为它已经踢了我的屁股了一段时间。
这是我的java代码：
public void init() {
int bufSize = AudioTrack.getMinBufferSize(44100,
AudioFormat.CHANNEL_OUT_STEREO,
AudioFormat.ENCODING_PCM_16BIT);
track = new AudioTrack(AudioManager.STREAM_MUSIC,
44100,
AudioFormat.CHANNEL_OUT_STEREO,
AudioFormat.ENCODING_PCM_16BIT,
bufSize,
AudioTrack.MODE_STREAM);
log("STARTING!!! _________________________ <--");
byte[] array = new byte[bufSize];
try {
fos = new FileOutputStream("/sdcard/acdc.bin");
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
decoder("/sdcard/acdc.ogg", array);
}
void playSound(byte[] buf, int size) {
try {
fos.write(buf, 0, size);
} catch (IOException e) {
e.printStackTrace();
}
if(track.getPlayState()!=AudioTrack.PLAYSTATE_PLAYING) {
track.play();
}
int wrote = track.write(buf, 0, size);
if (wrote != size)
log("WRITING: " + wrote + " but size was: " + size);
}
这是我的c函数：
void Java_com_example_ffmpegsample_MainActivity_decoder(JNIEnv* env, jobject obj,jstring file,jbyteArray array)
{
jboolean isfilenameCopy;
const char * filename = (*env)->GetStringUTFChars(env, file, &isfilenameCopy);
AVCodec *codec;
AVCodecContext *c= NULL;
AVFormatContext *pFormatCtx;
AVCodecContext *pCodecCtx;
int out_size, len;
FILE *f, *outfile;
uint8_t *outbuf;
uint8_t inbuf[AUDIO_INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
LOGI("HERE");
jclass cls = (*env)->GetObjectClass(env, obj);
LOGI(cls);
jmethodID play = (*env)->GetMethodID(env, cls, "playSound", "([BI)V");//At the begining of your main function
av_init_packet(&avpkt);
av_register_all();
LOGI("AUDIO DECODER");
printf("Audio decoding\n");
int err;
err = av_open_input_file(&pFormatCtx, filename, NULL, 0, NULL);
if (err!=0) {
LOGI("COULD NOT AV_OPEN file");
return;
}
if(av_find_stream_info(pFormatCtx)<0) {
LOGE("Unable to get stream info");
return;
}
int audioStream = -1;
int i;
for (i=0; i<pFormatCtx->nb_streams; i++) {
if(pFormatCtx->streams[i]->codec->codec_type==CODEC_TYPE_AUDIO) {
audioStream = i;
break;
}
}
if(audioStream==-1) {
LOGE("Unable to find audio stream");
return;
}
LOGI("Audio stream is [%d]", audioStream);
pCodecCtx=pFormatCtx->streams[audioStream]->codec;
codec = avcodec_find_decoder(pCodecCtx->codec_id);
/* find the mpeg audio decoder */
// codec = avcodec_find_decoder(CODEC_ID_AAC);
if (!codec) {
LOGI("NO CODEC");
fprintf(stderr, "codec not found\n");
return;
}
//c= avcodec_alloc_context();
c = pCodecCtx;
/* open it */
if (avcodec_open(c, codec) < 0) {
fprintf(stderr, "could not open codec\n");
LOGI("NOT LOADING CODEC");
return;
}
outbuf = malloc(AVCODEC_MAX_AUDIO_FRAME_SIZE);
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "could not open %s\n", filename);
LOGI("COULD NOT OPEN FILE");
return;
}
/* decode until eof */
avpkt.data = inbuf;
avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
while (avpkt.size > 0) {
LOGI("............................." + avpkt.size);
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");
LOGI("ERROR DECODING, error: %d", len);
return;
}
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);
}
答案 0 :(得分：1)
使用最小尺寸缓冲区在Streaming模式下创建AudioTrack。可能是因为它正在转换某些数据，然后写入一些数据，这些数据表明音频播放中存在间隙。如果转换必须继续从SD卡读取，则尤其如此。您可以增加AudioTrack缓冲区的大小以查看这是否是一个因素。
另外，我不确定，但我认为avcodec_decode_audio3可以将＆amp; out_size设置为大小，但是然后将其作为大小（以字节为单位）发送到AudioTrack。（不只是检查API及其字节）。
答案 1 :(得分：1)
您是否尝试在此类project中使用普通的CLI界面？ 您可以使用简单的fileProcesssor接口： IN = OGG OUT =原始PCM
请参阅下面的CLI，了解.ogg转换为PCM格式。然后对输出做任何事情
rob@ Downloads$ ffmpeg -i Example.ogg -f s16le -acodec pcm_s16le output.raw
ffmpeg version N-35901-g27a3415 Copyright (c) 2000-2012 the FFmpeg developers
built on Oct 7 2012 12:06:43 with gcc 4.6 (Ubuntu/Linaro 4.6.3-1ubuntu5)
configuration: --enable-gpl --enable-libfaac --enable-libfdk-aac --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-librtmp --enable-libtheora --enable-libvorbis --enable-libvpx --enable-x11grab --enable-libx264 --enable-nonfree --enable-version3
libavutil 51. 73.102 / 51. 73.102
libavcodec 54. 64.100 / 54. 64.100
libavformat 54. 29.105 / 54. 29.105
libavdevice 54. 3.100 / 54. 3.100
libavfilter 3. 19.102 / 3. 19.102
libswscale 2. 1.101 / 2. 1.101
libswresample 0. 16.100 / 0. 16.100
libpostproc 52. 1.100 / 52. 1.100
[NULL @ 0x186b840] Invalid packet
Input #0, ogg, from 'Example.ogg':
Duration: 00:00:06.10, start: 0.000000, bitrate: 137 kb/s
Stream #0:0: Audio: vorbis, 44100 Hz, stereo, s16, 160 kb/s
Output #0, s16le, to 'output.raw':
Metadata:
encoder : Lavf54.29.105
Stream #0:0: Audio: pcm_s16le, 44100 Hz, stereo, s16, 1411 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (vorbis -> pcm_s16le)
Press [q] to stop, [?] for help
size= 1054kB time=00:00:06.11 bitrate=1411.2kbits/s
video:0kB audio:1054kB subtitle:0 global headers:0kB muxing overhead 0.000000%
这假设您可以为具有OGG LIB依赖关系的android配置/生成ffmpeg，这可能是一个棘手的过程......