目标c中的音频文件格式问题

Question

我使用AVAudioRecorder编写了一个音频WAV（录制了我的声音）文件。最终的文件格式是WAV文件。文件已成功保存，我可以听到我的声音。我想将此文件发送到后端服务器（Web服务）。但我的服务器只接受WAV中的数据和FMT信息。它不接受我的wav文件，因为我的wav文件信息与FLLR，数据，FMT。我在Riffpad工具中检查了我的WAV文件信息。它显示FLLR，数据，FMT。但我只想要数据和fmt。因为我的服务器端只接受数据和FMT。那么请建议如何以编程方式删除我的wav文件中的FLLR？

我的记录源代码：

  NSError *error;

    // Recording settings
    NSMutableDictionary *settings = [NSMutableDictionary dictionary];
    [settings setValue: [NSNumber numberWithInt:kAudioFormatLinearPCM] forKey:AVFormatIDKey];
    [settings setValue: [NSNumber numberWithFloat:22050] forKey:AVSampleRateKey];
    [settings setValue: [NSNumber numberWithInt: 1] forKey:AVNumberOfChannelsKey]; // mono
    [settings setValue: [NSNumber numberWithInt:16] forKey:AVLinearPCMBitDepthKey];
    [settings setValue: [NSNumber numberWithBool:NO] forKey:AVLinearPCMIsBigEndianKey];
    //[settings setValue: [NSNumber numberWithInt:16] forKey:AudioSampleType];




    // File URL
    NSURL *url = [NSURL fileURLWithPath:FILEPATH];

    //NSLog(@"Url file path ::: %@",url);

    // Create recorder
    recorder = [[AVAudioRecorder alloc] initWithURL:url settings:settings error:&error];
    if (!recorder)
    {
//        NSLog(@"Error establishing recorder: %@", error.localizedFailureReason);
        return;
    }

Answer 1

感谢上帝和你的支持朋友。是的，最后我解决了我的问题。我不知道方式是否正确。但我的问题已经解决了。我使用上面的代码录制语音并保存我的音频。然后我将再次使用以下代码导出音频。我从https://developer.ibm.com/answers/questions/180732/seems-watson-text-to-speech-service-returns-a-wav.html

获得了此代码

-(NSData*) stripAndAddWavHeader:(NSData*) wav {
    unsigned long wavDataSize = [wav length] - 44;

    NSData *WaveFile= [NSMutableData dataWithData:[wav subdataWithRange:NSMakeRange(44, wavDataSize)]];

    NSMutableData *newWavData;
    newWavData = [self addWavHeader:WaveFile];

    return newWavData;
   }


 - (NSMutableData *)addWavHeader:(NSData *)wavNoheader {

       int headerSize = 44;
       long totalAudioLen = [wavNoheader length];
       long totalDataLen = [wavNoheader length] + headerSize-8;
       long longSampleRate = 22050.0;
       int channels = 1;
       long byteRate = 8 * 44100.0 * channels/8;



     Byte *header = (Byte*)malloc(44);
     header[0] = 'R';  // RIFF/WAVE header
     header[1] = 'I';
     header[2] = 'F';
     header[3] = 'F';
     header[4] = (Byte) (totalDataLen & 0xff);
     header[5] = (Byte) ((totalDataLen >> 8) & 0xff);
     header[6] = (Byte) ((totalDataLen >> 16) & 0xff);
     header[7] = (Byte) ((totalDataLen >> 24) & 0xff);
     header[8] = 'W';
     header[9] = 'A';
     header[10] = 'V';
     header[11] = 'E';
     header[12] = 'f';  // 'fmt ' chunk
     header[13] = 'm';
     header[14] = 't';
     header[15] = ' ';
     header[16] = 16;  // 4 bytes: size of 'fmt ' chunk
     header[17] = 0;
     header[18] = 0;
     header[19] = 0;
     header[20] = 1;  // format = 1
     header[21] = 0;
     header[22] = (Byte) channels;
     header[23] = 0;
     header[24] = (Byte) (longSampleRate & 0xff);
     header[25] = (Byte) ((longSampleRate >> 8) & 0xff);
     header[26] = (Byte) ((longSampleRate >> 16) & 0xff);
     header[27] = (Byte) ((longSampleRate >> 24) & 0xff);
     header[28] = (Byte) (byteRate & 0xff);
     header[29] = (Byte) ((byteRate >> 8) & 0xff);
     header[30] = (Byte) ((byteRate >> 16) & 0xff);
     header[31] = (Byte) ((byteRate >> 24) & 0xff);
     header[32] = (Byte) (2 * 8 / 8);  // block align
     header[33] = 0;
     header[34] = 16;  // bits per sample
     header[35] = 0;
     header[36] = 'd';
     header[37] = 'a';
     header[38] = 't';
     header[39] = 'a';
     header[40] = (Byte) (totalAudioLen & 0xff);
     header[41] = (Byte) ((totalAudioLen >> 8) & 0xff);
     header[42] = (Byte) ((totalAudioLen >> 16) & 0xff);
     header[43] = (Byte) ((totalAudioLen >> 24) & 0xff);

     NSMutableData *newWavData = [NSMutableData dataWithBytes:header length:44];
     [newWavData appendBytes:[wavNoheader bytes] length:[wavNoheader length]];
     return newWavData;
 }

Answer 2

在Swift上寻求数据边缘的解决方案

class MediaUtil {

private static func dataToUTF8String(data: NSData, offset: Int, length: Int) -> String? {
    let range = NSMakeRange(offset, length)
    let subdata = data.subdata(with: range)
    return String(data: subdata, encoding: String.Encoding.utf8)
}

private static func dataToUInt32(data: NSData, offset: Int) -> Int {
    var num: UInt32 = 0
    let length = 4
    let range = NSMakeRange(offset, length)
    data.getBytes(&num, range: range)
    return Int(num)
}

static func repairWAVHeader(data: NSMutableData)->Data {

    // resources for WAV header format:
    // [1] http://unusedino.de/ec64/technical/formats/wav.html
    // [2] http://soundfile.sapp.org/doc/WaveFormat/

    var newData = Data()

    // update RIFF chunk size
    let fileLength = data.length
    var riffChunkSize = UInt32(fileLength - 8)
    let riffChunkSizeRange = NSMakeRange(4, 4)
    data.replaceBytes(in: riffChunkSizeRange, withBytes: &riffChunkSize)

    // find data subchunk
    var subchunkID: String?
    var subchunkSize = 0
    var fieldOffset = 12
    let fieldSize = 4
    while true {
        // prevent running off the end of the byte buffer
        if fieldOffset + 2*fieldSize >= data.length {
            return newData
        }

        // read subchunk ID
        subchunkID = dataToUTF8String(data: data, offset: fieldOffset, length: fieldSize)
        fieldOffset += fieldSize
        if subchunkID == "data" {
            break
        }

        // read subchunk size
        subchunkSize = dataToUInt32(data: data, offset: fieldOffset)
        fieldOffset += fieldSize + subchunkSize
    }

    let rllrRange = NSMakeRange(0, fieldOffset)

    data.replaceBytes(in: rllrRange, withBytes: nil, length: 0)
    newData = newWavHeader(pcmDataLength: data.length)
    newData.append(data as Data)
    return newData
}

private static func newWavHeader(pcmDataLength: Int) -> Data {
    var header = Data()
    let headerSize = 44
    let bitsPerSample = Int32(16)
    let numChannels: Int32 = 1
    let sampleRate: Int32 = 16000

    // RIFF chunk descriptor
    let chunkID = [UInt8]("RIFF".utf8)
    header.append(chunkID, count: 4)

    var chunkSize = Int32(pcmDataLength + headerSize - 4).littleEndian
    let chunkSizePointer = UnsafeBufferPointer(start: &chunkSize, count: 1)
    header.append(chunkSizePointer)

    let format = [UInt8]("WAVE".utf8)
    header.append(format, count: 4)

    // "fmt" sub-chunk
    let subchunk1ID = [UInt8]("fmt ".utf8)
    header.append(subchunk1ID, count: 4)

    var subchunk1Size = Int32(16).littleEndian
    let subchunk1SizePointer = UnsafeBufferPointer(start: &subchunk1Size, count: 1)
    header.append(subchunk1SizePointer)

    var audioFormat = Int16(1).littleEndian
    let audioFormatPointer = UnsafeBufferPointer(start: &audioFormat, count: 1)
    header.append(audioFormatPointer)

    var headerNumChannels = Int16(numChannels).littleEndian
    let headerNumChannelsPointer = UnsafeBufferPointer(start: &headerNumChannels, count: 1)
    header.append(headerNumChannelsPointer)

    var headerSampleRate = Int32(sampleRate).littleEndian
    let headerSampleRatePointer = UnsafeBufferPointer(start: &headerSampleRate, count: 1)
    header.append(headerSampleRatePointer)

    var byteRate = Int32(sampleRate * numChannels * bitsPerSample / 8).littleEndian
    let byteRatePointer = UnsafeBufferPointer(start: &byteRate, count: 1)
    header.append(byteRatePointer)

    var blockAlign = Int16(numChannels * bitsPerSample / 8).littleEndian
    let blockAlignPointer = UnsafeBufferPointer(start: &blockAlign, count: 1)
    header.append(blockAlignPointer)

    var headerBitsPerSample = Int16(bitsPerSample).littleEndian
    let headerBitsPerSamplePointer = UnsafeBufferPointer(start: &headerBitsPerSample, count: 1)
    header.append(headerBitsPerSamplePointer)

    // "data" sub-chunk
    let subchunk2ID = [UInt8]("data".utf8)
    header.append(subchunk2ID, count: 4)

    var subchunk2Size = Int32(pcmDataLength).littleEndian
    let subchunk2SizePointer = UnsafeBufferPointer(start: &subchunk2Size, count: 1)

    header.append(subchunk2SizePointer)

    return header
}

}