iOS 将音频采样率从 16 kHz 转换为 8 kHz

Question

我尝试将 PCM 音频从 16kHz 转换为 8kHz，只是采样率，没有格式变化，流程看起来很简单，但我一直通过调用 AudioConverterFillComplexBuffer< 获取 kAudioConverterErr_InvalidInputSize ("insz")/。我的输入音频样本大小是 320 字节，结果应该是 160 字节，但我的输出缓冲区中只有 144 字节。在过去的几个小时里一直在扯我的头发。是不是设置错了？

static AudioConverterRef PCM8kTo16kConverterRef;

- (instancetype)init {
    self = [super init];
    if (self) {
        [self initConverter];
    }
    return self;
}

-(void)initConverter{
    AudioStreamBasicDescription PCM8kDescription = {0};
    PCM8kDescription.mSampleRate = 8000.0;
    PCM8kDescription.mFormatID = kAudioFormatLinearPCM;
    PCM8kDescription.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked | kAudioFormatFlagsNativeEndian;
    PCM8kDescription.mBitsPerChannel = 8 * sizeof(SInt16);
    PCM8kDescription.mChannelsPerFrame = 1;
    PCM8kDescription.mBytesPerFrame = sizeof(SInt16) * PCM8kDescription.mChannelsPerFrame;
    PCM8kDescription.mFramesPerPacket = 1;
    PCM8kDescription.mBytesPerPacket = PCM8kDescription.mBytesPerFrame * PCM8kDescription.mFramesPerPacket;

    AudioStreamBasicDescription PCM16kDescription = {0};
    PCM16kDescription.mSampleRate = 16000.0;
    PCM16kDescription.mFormatID = kAudioFormatLinearPCM;
    PCM16kDescription.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked | kAudioFormatFlagsNativeEndian;
    PCM16kDescription.mBitsPerChannel = 8 * sizeof(SInt16);
    PCM16kDescription.mChannelsPerFrame = 1;
    PCM16kDescription.mBytesPerFrame = sizeof(SInt16) * PCM16kDescription.mChannelsPerFrame;
    PCM16kDescription.mFramesPerPacket = 1;
    PCM16kDescription.mBytesPerPacket = PCM16kDescription.mBytesPerFrame * PCM16kDescription.mFramesPerPacket;

    OSStatus status = AudioConverterNew(&PCM16kDescription, &PCM8kDescription, &converterRef);
}

OSStatus inInputDataProc(AudioConverterRef inAudioConverter, UInt32 *ioNumberDataPackets, AudioBufferList *ioData, AudioStreamPacketDescription **outDataPacketDescription, void *inUserData)
{
    AudioBufferList audioBufferList = *(AudioBufferList *)inUserData;

    ioData->mBuffers[0].mData = audioBufferList.mBuffers[0].mData;
    ioData->mBuffers[0].mDataByteSize = audioBufferList.mBuffers[0].mDataByteSize;

    return  noErr;
}

- (NSData *)testSample:(NSData *)inAudio {

    NSMutableData *ddd = [inAudio mutableCopy];
    AudioBufferList inAudioBufferList = {0};
    inAudioBufferList.mNumberBuffers = 1;
    inAudioBufferList.mBuffers[0].mNumberChannels = 1;
    inAudioBufferList.mBuffers[0].mDataByteSize = (UInt32)[ddd length];
    inAudioBufferList.mBuffers[0].mData = [ddd mutableBytes];

    uint32_t bufferSize = (UInt32)[inAudio length] / 2;
    uint8_t *buffer = (uint8_t *)malloc(bufferSize);
    memset(buffer, 0, bufferSize);
    AudioBufferList outAudioBufferList;
    outAudioBufferList.mNumberBuffers = 1;
    outAudioBufferList.mBuffers[0].mNumberChannels = 1;
    outAudioBufferList.mBuffers[0].mDataByteSize = bufferSize;
    outAudioBufferList.mBuffers[0].mData = buffer;

    UInt32 ioOutputDataPacketSize = bufferSize;

    OSStatus ret = AudioConverterFillComplexBuffer(converterRef, inInputDataProc, &inAudioBufferList, &ioOutputDataPacketSize, &outAudioBufferList, NULL) ;

    NSData *data = [NSData dataWithBytes:outAudioBufferList.mBuffers[0].mData length:outAudioBufferList.mBuffers[0].mDataByteSize];
    free(buffer);
    return data;
}

Answer 1

有两个问题:

1. 您的AudioConverterComplexInputDataProc 没有设置ioNumberDataPackets:

   *ioNumberDataPackets = audioBufferList.mBuffers[0].mDataByteSize/2;
   

2. ioOutputDataPacketSize 应该是以数据包/帧为单位的输出缓冲区容量，而不是字节，所以你不应该除以 2 吗？