private void Recognize(ref string result, int sampleRate)
{
amplitudeSum = 0.0f;
for (int i = 0; i < playingAudioSpectrum.Length; ++i)
{
amplitudeSum += playingAudioSpectrum[i];
}
if (amplitudeSum >= amplitudeThreshold)
{
MathToolBox.Convolute(playingAudioSpectrum, gaussianFilter, MathToolBox.EPaddleType.Repeat, smoothedAudioSpectrum);
MathToolBox.FindLocalLargestPeaks(smoothedAudioSpectrum, peakValues, peakPositions);
frequencyUnit = sampleRate / windowSize;
for (int i = 0; i < formantArray.Length; ++i)
{
formantArray[i] = peakPositions[i] * frequencyUnit;
}
for (int i = 0; i < currentVowelFormantCeilValues.Length; ++i)
{
if (formantArray[0] > currentVowelFormantCeilValues[i])
{
result = currentVowels[i];
}
}
}
}
public string[] RecognizeAllByAudioClip(AudioClip audioClip)
{
int recognizeSampleCount = Mathf.CeilToInt((float)(audioClip.samples) / (float)(shiftStepSize));
string[] result = new string[recognizeSampleCount];
float[] currentAudioData = new float[this.windowSize];
float[] currentAudioSpectrum = new float[this.windowSize];
for (int i = 0; i < recognizeSampleCount; ++i)
{
audioClip.GetData(currentAudioData, i * shiftStepSize);
for (int j = 0; j < windowSize; ++j)
{
currentAudioData[j] *= windowArray[j];
}
currentAudioSpectrum = MathToolBox.DiscreteCosineTransform(currentAudioData);
amplitudeSum = 0.0f;
for (int k = 0; k < windowSize; ++k)
{
amplitudeSum += currentAudioSpectrum[k];
}
if (amplitudeSum >= amplitudeThreshold)
{
MathToolBox.Convolute(currentAudioSpectrum, gaussianFilter, MathToolBox.EPaddleType.Repeat, smoothedAudioSpectrum);
MathToolBox.FindLocalLargestPeaks(smoothedAudioSpectrum, peakValues, peakPositions);
frequencyUnit = audioClip.frequency / 2 / windowSize;
for (int l = 0; l < formantArray.Length; ++l)
{
formantArray[l] = peakPositions[l] * frequencyUnit;
}
for (int m = 0; m < currentVowelFormantCeilValues.Length; ++m)
{
if (formantArray[0] > currentVowelFormantCeilValues[m])
{
result[i] = currentVowels[m];
}
}
}
}
return(result);
}
