0

我已经设置了一个类来将音频从一种格式转换为另一种给定的输入和输出AudioStreamBasicDescription。AudioUnitRender当我将线性 PCM 从麦克风转换为 iLBC 时，当我从该函数中给它 1024 个数据包时，它可以工作并给我 6 个数据包。然后我通过 UDP 将这 226 个字节发送到在不同设备上运行的同一个应用程序。问题是，当我使用相同的类转换回线性 PCM 以提供音频单元输入时，该AudioConverterFillComplexBuffer函数不会提供 1024 个数据包，而是提供 960 ... 这意味着音频单元输入需要 4096 个字节（立体声为 2048 x 2）但我只能给它 3190 左右，所以听起来真的很脆而且失真......

如果我给AudioConverter1024 个 LinearPCM 数据包，转换为 iLBC，再转换回 LinearPCM，我肯定应该再次获得 1024 个数据包吗？

音频转换器功能：

-(void) doConvert {

    // Start converting
    if (converting) return;
    converting = YES;

    while (true) {

        // Get next buffer
        id bfr = [buffers getNextBuffer];
        if (!bfr) {
            converting = NO;
            return;
        }

        // Get info
        NSArray* bfrs = ([bfr isKindOfClass:[NSArray class]] ? bfr : @[bfr]);
        int bfrSize = 0;
        for (NSData* dat in bfrs) bfrSize += dat.length;

        int inputPackets = bfrSize / self.inputFormat.mBytesPerPacket;
        int outputPackets = (inputPackets * self.inputFormat.mFramesPerPacket) / self.outputFormat.mFramesPerPacket;

        // Create output buffer
        AudioBufferList* bufferList = (AudioBufferList*) malloc(sizeof(AudioBufferList) * self.outputFormat.mChannelsPerFrame);
        bufferList -> mNumberBuffers = self.outputFormat.mChannelsPerFrame;
        for (int i = 0 ; i < self.outputFormat.mChannelsPerFrame ; i++) {
            bufferList -> mBuffers[i].mNumberChannels = 1;
            bufferList -> mBuffers[i].mDataByteSize = 4*1024;
            bufferList -> mBuffers[i].mData = malloc(bufferList -> mBuffers[i].mDataByteSize);
        }

        // Create input buffer
        AudioBufferList* inputBufferList = (AudioBufferList*) malloc(sizeof(AudioBufferList) * bfrs.count);
        inputBufferList -> mNumberBuffers = bfrs.count;
        for (int i = 0 ; i < bfrs.count ; i++) {
            inputBufferList -> mBuffers[i].mNumberChannels = 1;
            inputBufferList -> mBuffers[i].mDataByteSize = [[bfrs objectAtIndex:i] length];
            inputBufferList -> mBuffers[i].mData = (void*) [[bfrs objectAtIndex:i] bytes];
        }

        // Create sound data payload
        struct SoundDataPayload payload;
        payload.data = inputBufferList;
        payload.numPackets = inputPackets;
        payload.packetDescriptions = NULL;
        payload.used = NO;

        // Convert data
        UInt32 numPackets = outputPackets;
        OSStatus err = AudioConverterFillComplexBuffer(converter, acvConverterComplexInput, &payload, &numPackets, bufferList, NULL);
        if (err)
            continue;

        // Check how to output
        if (bufferList -> mNumberBuffers > 1) {

            // Output as array
            NSMutableArray* array = [NSMutableArray arrayWithCapacity:bufferList -> mNumberBuffers];
            for (int i = 0 ; i < bufferList -> mNumberBuffers ; i++)
                [array addObject:[NSData dataWithBytes:bufferList -> mBuffers[i].mData length:bufferList -> mBuffers[i].mDataByteSize]];

            // Save
            [convertedBuffers addBuffer:array];

        } else {

            // Output as data
            NSData* newData = [NSData dataWithBytes:bufferList -> mBuffers[0].mData length:bufferList -> mBuffers[0].mDataByteSize];

            // Save
            [convertedBuffers addBuffer:newData];

        }

        // Free memory
        for (int i = 0 ; i < bufferList -> mNumberBuffers ; i++)
            free(bufferList -> mBuffers[i].mData);

        free(inputBufferList);
        free(bufferList);

        // Tell delegate
        if (self.convertHandler)
            //dispatch_async(dispatch_get_main_queue(), self.convertHandler);
            self.convertHandler();

    }

}

转换为 iLBC 时的格式：

// Get input format from mic
UInt32 size = sizeof(AudioStreamBasicDescription);
AudioStreamBasicDescription inputDesc;
AudioUnitGetProperty(self.ioUnit, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Output, 1, &inputDesc, &size);

// Set output stream description
size = sizeof(AudioStreamBasicDescription);
AudioStreamBasicDescription outputDescription;
memset(&outputDescription, 0, size);
outputDescription.mFormatID         = kAudioFormatiLBC;
OSStatus err = AudioFormatGetProperty(kAudioFormatProperty_FormatInfo, 0, NULL, &size, &outputDescription);

从 iLBC 转换时的格式：

// Set input stream description
size = sizeof(AudioStreamBasicDescription);
AudioStreamBasicDescription inputDescription;
memset(&inputDescription, 0, size);
inputDescription.mFormatID        = kAudioFormatiLBC;
AudioFormatGetProperty(kAudioFormatProperty_FormatInfo, 0, NULL, &size, &inputDescription);

// Set output stream description
UInt32 size = sizeof(AudioStreamBasicDescription);
AudioStreamBasicDescription outputDesc;
AudioUnitGetProperty(unit, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Input, 0, &outputDesc, &size);
4

1 回答 1

1

您必须使用中间缓冲区从足够多的传入数据包中保存足够的字节，以完全匹配音频单元输入请求的数量。依赖于任何一个压缩格式的 UDP 数据包来完全正确的大小是行不通的。

AudioConverter 可以缓冲样本并根据压缩格式更改数据包大小。

于 2012-12-05T16:36:48.633 回答