I'm attempting to use the SoundTouch C++ library for audio speed and pitch changes in an Android app. I have successfully pushed a Java byte[] array (from a .wav) through JNI, returned it, and played it back with an AudioTrack
.
The next step is attempting to push a sample byte[] through the SoundTouch pipeline. I have dissected the source of the SoundStretch console program included with the library and have attempted to adapt it. I am using a stereo, 16-bit source for testing purposes.
With my current temporary setup I am ignoring the RIFF header and converting it along with the .wav data because the Java AudioTrack
object does not need to read the header, it just plays raw PCM. Playing the raw byte[] without sending through SoundTouch just results in a small click where the header is.
After sending through the SoundTouch pipeline, I am playing back white noise where the beginning of the audio is supposed to be. I assume I am having a problem at the end of my write()
function, where I am casting short's to signed chars. Here, the console app is writing to a file, instead of pushing to a vector:
int res = (int)fwrite(temp, 1, numBytes, fptr);
I have read the documentation for fwrite
but I don't know enough about bit twiddling or audio processing to know what to do here to correctly get this information in a char[] instead of writing to a file. I know I am loosing information with the cast, but I am unsure of how to correct it.
In case anyone is extra motivated, the SoundStretch source can be found here: http://www.surina.net/soundtouch/sourcecode.html
extern "C" DLL_PUBLIC jbyteArray
Java_net_surina_soundtouch_SoundTouch_getMutatedBytes
(JNIEnv *env, jobject thiz, jbyteArray input, jint length)
{
const int BUFF_SIZE = 2048000;
SoundTouch soundTouch;
jboolean isCopy;
jbyte* ar = env->GetByteArrayElements(input, &isCopy);
signed char* cBufferIn = (signed char*)ar;
SAMPLETYPE* fBufferIn = new SAMPLETYPE[length];
vector<signed char> fBufferOut;
//converts the chars to floats per the SoundTouch console app.
convertInput16(cBufferIn, fBufferIn, length);
//channels, sampling rate, speed, pitch change
setup(&soundTouch, 2, 44100, 1.0, 0);
//transform floats from fBufferIn to fBufferout
process(&soundTouch, fBufferIn, fBufferOut, BUFF_SIZE);
signed char* res = &fBufferOut[0];
jbyteArray result = env->NewByteArray(length);
env->SetByteArrayRegion(result, 0, fBufferOut.size(), res);
LOGV("fBufferOut Size: %d", fBufferOut.size());
delete[] fBufferIn;
return result;
}
process():
static void process(SoundTouch* soundTouch, SAMPLETYPE* fBufferIn, vector<signed char>& fBufferOut, int BUFF_SIZE)
{
int nSamples = BUFF_SIZE / 2; //2 bytes per sample, using 16 bit sample for testing
int buffSizeSamples = BUFF_SIZE / 2; //2 channel stereo
soundTouch->putSamples(fBufferIn, nSamples);
do
{
nSamples = soundTouch->receiveSamples(fBufferIn, buffSizeSamples);
write(fBufferIn, fBufferOut, nSamples / 2); //2 channels
} while (nSamples != 0);
soundTouch->flush();
do
{
nSamples = soundTouch->receiveSamples(fBufferIn, buffSizeSamples);
write(fBufferIn, fBufferOut, nSamples / 2);
LOGV("NUMBER OF SAMPLES: %d", nSamples);
} while (nSamples != 0);
}
write():
static void write(const float *bufferIn, vector<signed char>& bufferOut, int numElems)
{
int numBytes;
int bytesPerSample;
if (numElems == 0) return;
bytesPerSample = 16 / 8; //16 bit test sample / bits in a byte
numBytes = numElems * bytesPerSample;
short *temp = (short*)getConvBuffer(numBytes);
switch (bytesPerSample)
{
case 2: //16 bit encoding per the SoundStretch console app
{
short *temp2 = (short *)temp;
for (int i = 0; i < numElems; i++)
{
short value = (short)saturate(bufferIn[i] * 32768.0f, -32768.0f, 32767.0f); //magic to me
temp2[i] = value; //works for little endian only.
}
break;
}
default:
assert(false);
}
for (int i = 0; i < numElems; ++i)
{
bufferOut.push_back((signed char)temp[i]); //I think my problem is here.
}
delete[] temp;
//bytesWritten += numBytes;
}