public SampleDataAsset(string name, WaveFile wave)
{
if (name == null)
throw new ArgumentNullException("An asset must be given a valid name.");
assetName = name;
SamplerChunk smpl = wave.FindChunk<SamplerChunk>();
if (smpl != null)
{
sampleRate = (int)(44100.0 * (1.0 / (smpl.SamplePeriod / 22675.0)));
rootKey = (short)smpl.UnityNote;
tune = (short)(smpl.PitchFraction * 100);
if (smpl.Loops.Length > 0)
{
//--WARNING ASSUMES: smpl.Loops[0].Type == SamplerChunk.SampleLoop.LoopType.Forward
loopStart = smpl.Loops[0].Start;
loopEnd = smpl.Loops[0].End + smpl.Loops[0].Fraction + 1;
}
}
else
{
sampleRate = wave.Format.SampleRate;
}
byte[] data = wave.Data.RawSampleData;
if (wave.Format.ChannelCount != audioChannels) //reformat to supported channels
data = WaveHelper.GetChannelPcmData(data, wave.Format.BitsPerSample, wave.Format.ChannelCount, audioChannels);
sampleData = PcmData.Create(wave.Format.BitsPerSample, data, true);
start = 0;
end = sampleData.Length;
}
public SampleAsset(string name, WaveFile wf)
{
Name = name;
Channels = (byte)wf.Format.ChannelCount;
Bits = (byte)wf.Format.BitsPerSample;
SamplerChunk smpl = wf.FindChunk<SamplerChunk>();
if (smpl != null)
{
SampleRate = (int)(44100.0 * (1.0 / (smpl.SamplePeriod / 22675.0)));
RootKey = (short)smpl.UnityNote;
Tune = (short)(smpl.PitchFraction * 100);
if (smpl.Loops.Length > 0)
{
if (smpl.Loops[0].Type != SamplerChunk.SampleLoop.LoopType.Forward)
Console.WriteLine("Warning: Loopmode was not supported on asset: " + Name);
LoopStart = smpl.Loops[0].Start;
LoopEnd = smpl.Loops[0].End + smpl.Loops[0].Fraction + 1;
}
}
else
{
SampleRate = wf.Format.SampleRate;
}
SampleRate = wf.Format.SampleRate;
Data = wf.Data.RawSampleData;
}
/// <summary>
/// Decodes the ogg-vorbis file
/// </summary>
/// <param name="input">Stream of the ogg-vorbis file</param>
/// <returns>PCM-Wave version of the input</returns>
public WaveFile Decode(Stream input)
{
MemoryStream output = new MemoryStream();
WaveFile wf = new WaveFile();
VorbisFile vf = new VorbisFile((FileStream)input, null, 0);
Info inf = vf.getInfo(-1);
wf.Channels = (short)inf.channels;
wf.Frequency = inf.rate;
wf.Bits = 16;
Axiom.Core.LogManager.Instance.Write("SoundSystem: File is Ogg Vorbis "+inf.version.ToString()+" "+inf.rate.ToString()+"Hz, "+inf.channels.ToString()+" channels");
int bufferlen = 4096;
int result = 1;
byte[] buffer = new byte[bufferlen];
int[] section = new int[1];
while(result != 0)
{
result = vf.read(buffer, bufferlen, 0, 2, 1, section);
output.Write(buffer, 0, result);
}
output.Seek(0, SeekOrigin.Begin);
wf.Data = output;
return wf;
}
protected void OpenExistingFile(WaveFile file)
{
// only open file if it's not already open
MdiForm match = (MdiForm)MdiChildren.FirstOrDefault(f => ((MdiForm)f).Wave == file);
if (match != null)
{
match.Activate();
return;
}
MdiForm graphForm = new MdiForm(file);
graphForm.MdiParent = this;
graphForm.Show();
//_menuWindow.
// start tracking the current directory
var directory = Path.GetDirectoryName(file.filePath);
WaveManagerBusiness.WaveManager.AddDirectory(directory);
// redraw the file list in the left panel
WaveManagerBusiness.WaveManager.FireRepaintFileList();
}
public DiscreteSignal WaveToSignal(WaveFile waveFile)
{
return(waveFile[Channels.Average]);
}
private void button1_Click(object sender, EventArgs e)
{
WaveFile wff = new WaveFile(textBox1.Text);
}
void Start()
{
AudioClip clip;
float[] data;
double[] data2;
double sampleRate;
int channels;
using (var stream = System.IO.File.OpenRead(filePath)) {
var waveFile = new WaveFile(stream);
clip = AudioClip.Create("test", waveFile.Samples.Length / waveFile.Channels, channels = waveFile.Channels, (int)waveFile.SamplePerSec, false);
songLength = (float)waveFile.Samples.Length / waveFile.SamplePerSec / waveFile.Channels;
data = new float[waveFile.Samples.Length];
data2 = new double[waveFile.Samples.Length / waveFile.Channels];
sampleRate = waveFile.SamplePerSec;
for (int i = 0; i < data.Length; i++)
{
data[i] = (float)waveFile.Samples[i];
}
for (int i = 0; i < data2.Length; i++)
{
data2[i] = waveFile.Samples[i * waveFile.Channels];
}
clip.SetData(data, 0);
}
const int length = 2048;
const int skip = 512;
const int width = length >> 3;
var com = new Complex[length];
var texture = new Texture2D(width, data.Length / channels / skip, TextureFormat.RGB24, false);
texture.filterMode = FilterMode.Point;
Debug.Log(texture.height);
Debug.Log(texture.width);
if (System.IO.File.Exists(filePath + ".png"))
{
texture.LoadImage(System.IO.File.ReadAllBytes(filePath + ".png"));
}
else
{
for (int i = 0; i < data.Length / channels / skip; i++)
{
if (i * skip * channels + length * channels >= data.Length)
{
break;
}
for (int j = 0; j < length; j++)
{
com[j].real = data[i * skip * channels + j * channels];
com[j].img = 0;
}
com = FFT.CalculateFFT(com, false);
for (int j = 0; j < width; j++)
{
texture.SetPixel(width - j - 1, i, gradient.Evaluate(com[j].fMagnitude * 5));
}
}
}
texture.Apply();
uiRawImage.texture = texture;
// uiRawImage.SetNativeSize();
beatmapEditor.Init(clip.length, 2, 0);
System.IO.File.WriteAllBytes(filePath + ".png", texture.EncodeToPNG());
source.clip = clip;
}
private static AudioClip LoadAudio(byte[] data)
{
//TODO handling for things that aren't WAV
return(WaveFile.Load(data, false).ToAudioClip());
}
// Open file
private void openToolStripMenuItem_Click(object sender, EventArgs e)
{
spectrumPanel.refresh();
signalPanel.refresh();
signalPanel.Stride = 64;
var ofd = new OpenFileDialog();
if (ofd.ShowDialog() != DialogResult.OK)
{
return;
}
txtFilePath.Text = ofd.FileName;
_waveFileName = ofd.FileName;
try
{
using (var stream = new FileStream(_waveFileName, FileMode.Open))
{
IAudioContainer waveFile = new WaveFile(stream);
_signal = waveFile[Channels.Left];
_signal_storage = _signal;
}
}
catch (IOException ex)
{
Console.WriteLine("Error reading from {0}. Message = {1}", _waveFileName, ex.Message);
}
// Get duration
WaveFileReader wf = new WaveFileReader(_waveFileName);
var totalTime = wf.TotalTime;
txtTotalTime.Text = totalTime.TotalMilliseconds.ToString() + " ms";
signalPanel.max_time_value = (float)totalTime.TotalMilliseconds;
var max_value = _signal[0];
var count = 0;
for (int i = 1; i < _signal.Length; i++)
{
if (max_value < _signal[i])
{
max_value = _signal[i];
}
if (_signal[i] > 0.2)
{
count++;
}
}
txtMaxValue.Text = max_value.ToString();
signalPanel.Signal = _signal;
_fftSize = int.Parse(fftSizeTextBox.Text);
_cepstrumSize = int.Parse(cepstrumSizeTextBox.Text);
_hopSize = int.Parse(hopSizeTextBox.Text);
_fft = new Fft(_fftSize);
_cepstralTransform = new CepstralTransform(_cepstrumSize, _fftSize);
var pitchTracker = new Pitch((float)_fftSize / _signal.SamplingRate,
(float)_hopSize / _signal.SamplingRate);
_pitchTrack = pitchTracker.Track(_signal);
// Show chart in frequency domain
UpdateAutoCorrelation();
UpdateSpectra();
// obtain spectrogram
_stft = new Stft(_fftSize, _hopSize, WindowTypes.Rectangular);
var spectrogram = _stft.Spectrogram(_signal);
specNoComboBox.DataSource = Enumerable.Range(1, _pitchTrack.Count).ToArray();
_specNo = 0;
spectrumPanelAfterFilter.refresh();
signalPanelAfterFilter.refresh();
lblNote.Visible = false;
savePWMDataToolStripMenuItem.Enabled = true;
}
public void Stop()
{
if (_inputType == InputType.Plugin && _frontend != null)
{
_frontend.Stop();
_frontend = null;
}
if (_wavePlayer != null)
{
_wavePlayer.Dispose();
_wavePlayer = null;
}
if (_waveRecorder != null)
{
_waveRecorder.Dispose();
_waveRecorder = null;
}
if (_waveDuplex != null)
{
_waveDuplex.Dispose();
_waveDuplex = null;
}
_inputSampleRate = 0;
if (_waveReadThread != null)
{
_waveReadThread.Join();
_waveReadThread = null;
}
if (_iqStream != null)
{
_iqStream.Close();
}
if (_audioStream != null)
{
_audioStream.Close();
}
if (_streamHookManager != null)
{
_streamHookManager.CloseStreams();
_streamHookManager.Stop();
}
if (_dspThread != null)
{
_dspThread.Join();
_dspThread = null;
}
if (_streamHookManager != null)
{
_streamHookManager.StopIQObserverThread();
}
if (_waveFile != null)
{
_waveFile.Dispose();
_waveFile = null;
}
if (_iqStream != null)
{
_iqStream.Dispose();
_iqStream = null;
}
if (_streamHookManager != null)
{
_streamHookManager.DisposeStreams();
}
_audioStream = null;
_dspOutBuffer = null;
_iqInBuffer = null;
}
public Invert(WaveFile waveFile)
{
this.waveFile = waveFile;
}
/// <summary>
/// Generates the specified dual-tone multi-frequencies <paramref name="repeatCount"/> times storing them in the specified <see cref="WaveFile"/>.
/// </summary>
/// <param name="destination"><see cref="WaveFile"/> used to store generated dual-tone multi-frequencies.</param>
/// <param name="tones">Dual-tone multi-frequencies to generate.</param>
/// <param name="volume">Volume of generated dual-tones as a percentage (0 to 1).</param>
/// <param name="repeatCount">Number of times to repeat each tone.</param>
/// <exception cref="ArgumentOutOfRangeException">Value must be expressed as a fractional percentage between zero and one.</exception>
/// <exception cref="InvalidOperationException"><see cref="DTMF"/> only generated for <see cref="WaveFile"/> with a sample rate of 8, 16, 24, 32 or 64 bits per sample.</exception>
public static void Generate(WaveFile destination, DTMF[] tones, double volume, int repeatCount)
{
if (volume < 0.0D || volume > 1.0D)
throw new ArgumentOutOfRangeException("volume", "Value must be expressed as a fractional percentage between zero and one");
double amplitude = destination.AmplitudeScalar * volume;
// Iterate through each repeat count
for (int x = 0; x < repeatCount; x++)
{
// Interate through each tone
foreach (DTMF tone in tones)
{
// Iterate through each sample for total DTMF duration
for (long y = 0; y < tone.Duration * destination.SampleRate; y++)
{
// Compute frequencies of DTMF at given time and add to wave file
destination.AddSample(DTMF.ComputeFrequencies(tone, y, destination.SampleRate) * amplitude);
}
}
}
}
async public void extractFeatures(string _filepath, StorageFile sf)
{
op = new float[10];
tdVectors = new List <float[]>();
mfccVectors = new List <float[]>();
featureTimeList = new List <float[]>();
//NWaves
FilePath = _filepath;
PredictedLabel = "Ready!.";
//player.Load(GetStreamFromFile(FilePath));
//player.Play();
mMedia.Source = MediaSource.CreateFromStorageFile(sf);
bool test = player.IsPlaying;
mMedia.AutoPlay = true;
MusicProperties properties = await sf.Properties.GetMusicPropertiesAsync();
TimeSpan myTrackDuration = properties.Duration;
duration = Convert.ToInt32(myTrackDuration.TotalSeconds);
if (FilePath != null)
{
DiscreteSignal signal;
// load
var mfcc_no = 24;
var samplingRate = 44100;
var mfccOptions = new MfccOptions
{
SamplingRate = samplingRate,
FeatureCount = mfcc_no,
FrameDuration = 0.025 /*sec*/,
HopDuration = 0.010 /*sec*/,
PreEmphasis = 0.97,
Window = WindowTypes.Hamming
};
var opts = new MultiFeatureOptions
{
SamplingRate = samplingRate,
FrameDuration = 0.025,
HopDuration = 0.010
};
var tdExtractor = new TimeDomainFeaturesExtractor(opts);
var mfccExtractor = new MfccExtractor(mfccOptions);
// Read from file.
featureString = String.Empty;
featureString = $"green,";
//MFCC
var mfccList = new List <List <double> >();
var tdList = new List <List <double> >();
//MFCC
//TD Features
//Spectral features
for (var i = 0; i < mfcc_no; i++)
{
mfccList.Add(new List <double>());
}
for (var i = 0; i < 4; i++)
{
tdList.Add(new List <double>());
}
string specFeatures = String.Empty;
Console.WriteLine($"{tag} Reading from file");
using (var stream = new FileStream(FilePath, FileMode.Open))
{
var waveFile = new WaveFile(stream);
signal = waveFile[channel : Channels.Left];
////Compute MFCC
float[] mfvfuck = new float[25];
var sig_sam = signal.Samples;
mfccVectors = mfccExtractor.ComputeFrom(sig_sam);
var fftSize = 1024;
tdVectors = tdExtractor.ComputeFrom(signal.Samples);
var fft = new Fft(fftSize);
var resolution = (float)samplingRate / fftSize;
var frequencies = Enumerable.Range(0, fftSize / 2 + 1)
.Select(f => f * resolution)
.ToArray();
var spectrum = new Fft(fftSize).MagnitudeSpectrum(signal).Samples;
var centroid = Spectral.Centroid(spectrum, frequencies);
var spread = Spectral.Spread(spectrum, frequencies);
var flatness = Spectral.Flatness(spectrum, 0);
var noiseness = Spectral.Noiseness(spectrum, frequencies, 3000);
var rolloff = Spectral.Rolloff(spectrum, frequencies, 0.85f);
var crest = Spectral.Crest(spectrum);
var decrease = Spectral.Decrease(spectrum);
var entropy = Spectral.Entropy(spectrum);
specFeatures = $"{centroid},{spread},{flatness},{noiseness},{rolloff},{crest},{decrease},{entropy}";
//}
Console.WriteLine($"{tag} All features ready");
for (int calibC = 0; calibC < mfccVectors.Count;)
{
featureString = String.Empty;
var tmp = new ModelInput();
for (var j = 0; j < (mfccVectors.Count / duration) - 1 && calibC < mfccVectors.Count; j++)
{
for (var i = 0; i < mfcc_no; i++)
{
mfccList[i].Add(mfccVectors[calibC][i]);
}
for (var i = 0; i < 4; i++)
{
tdList[i].Add(tdVectors[calibC][i]);
}
calibC += 1;
}
var mfcc_statistics = new List <double>();
for (var i = 0; i < mfcc_no; i++)
{
//preheader += m + "_mean";
//preheader += m + "_min";
//preheader += m + "_var";
//preheader += m + "_sd";
//preheader += m + "_med";
//preheader += m + "_lq";
//preheader += m + "_uq";
//preheader += m + "_skew";
//preheader += m + "_kurt";
mfcc_statistics.Add(Statistics.Mean(mfccList[i]));
mfcc_statistics.Add(Statistics.Minimum(mfccList[i]));
mfcc_statistics.Add(Statistics.Variance(mfccList[i]));
mfcc_statistics.Add(Statistics.StandardDeviation(mfccList[i]));
mfcc_statistics.Add(Statistics.Median(mfccList[i]));
mfcc_statistics.Add(Statistics.LowerQuartile(mfccList[i]));
mfcc_statistics.Add(Statistics.UpperQuartile(mfccList[i]));
mfcc_statistics.Add(Statistics.Skewness(mfccList[i]));
mfcc_statistics.Add(Statistics.Kurtosis(mfccList[i]));
}
var td_statistics = new List <double>();
for (var i = 0; i < 4; i++)
{
td_statistics.Add(Statistics.Mean(tdList[i]));
td_statistics.Add(Statistics.Minimum(tdList[i]));
td_statistics.Add(Statistics.Variance(tdList[i]));
td_statistics.Add(Statistics.StandardDeviation(tdList[i]));
td_statistics.Add(Statistics.Median(tdList[i]));
td_statistics.Add(Statistics.LowerQuartile(tdList[i]));
td_statistics.Add(Statistics.UpperQuartile(tdList[i]));
td_statistics.Add(Statistics.Skewness(tdList[i]));
td_statistics.Add(Statistics.Kurtosis(tdList[i]));
}
// Write MFCCs
featureString += String.Join(",", mfcc_statistics);
featureString += ",";
featureString += String.Join(",", td_statistics);
//Write Spectral features as well
featureString += ",";
featureString += specFeatures;
Console.WriteLine($"{tag} Feature String ready {featureString}");
if (File.Exists(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp")))
{
File.Delete(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp"));
File.WriteAllText(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp"), featureString);
}
else
{
File.WriteAllText(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp"), featureString);
}
MLContext mLContext = new MLContext();
string fileName = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp");
IDataView dataView = mLContext.Data.LoadFromTextFile <ModelInput>(
path: fileName,
hasHeader: false,
separatorChar: ',',
allowQuoting: true,
allowSparse: false);
// Use first line of dataset as model input
// You can replace this with new test data (hardcoded or from end-user application)
ModelInput sampleForPrediction = mLContext.Data.CreateEnumerable <ModelInput>(dataView, false)
.First();
ModelOutput opm = ConsumeModel.Predict(sampleForPrediction);
featureTimeList.Add(opm.Score);
Console.WriteLine($"{tag} Feature vs time list ready");
}
//Console.WriteLine($"{tag} MFCC: {mfccVectors.Count}");
//Console.WriteLine($"{tag} TD: {tdVectors.Count}");
//Console.WriteLine($"{tag} featureTimeArray: {featureTimeList.Count} {featureString}");
}
}
playAudio();
}
public void Render(ScriptPortal.Vegas.Vegas myVegas)
{
SetProgressBounds(Count);
using (UndoBlock undo = new UndoBlock("Render tracks"))
{
for (int i = 0; i < Count; i++)
{
var ri = this[i];
foreach (var trk in myVegas.Project.Tracks)
{
trk.Mute = !ri.Tracks.Contains(trk);
}
// padding
if (ri.RenderParams.GetParam <bool>(RenderTags.DoPadding))
{
if (ri.RenderTemplate.RendererID != myVegas.Renderers.FindByName("Wave (Microsoft)").ID)
{
ErrorLog(
String.Format(
"The region {0} could not be padded. Padded rendering can only be performed on .WAV (PCM) files.",
ri.Region.Label));
}
else
{
var paddingTime = Timecode.FromSeconds(ri.PaddingSeconds);
if (ri.Start - paddingTime < myVegas.Project.Ruler.StartTime)
{
ErrorLog(String.Format(
"The region {0} could not be padded. Move your region further into the project.", ri.Region.Label));
}
else
{
ri.Start -= paddingTime;
ri.Length += paddingTime;
ri.Length += paddingTime;
}
}
}
if (File.Exists(ri.FilePath) && ri.RenderParams.GetParam <bool>(RenderTags.DoReadonly))
{
// check readonly
var attr = File.GetAttributes(ri.FilePath);
if (attr.IsSet(FileAttributes.ReadOnly))
{
File.SetAttributes(ri.FilePath, attr & ~FileAttributes.ReadOnly);
}
}
SetProgress(i);
SetProgressStatus("Rendering " + ri.FilePath);
RenderStatus status = myVegas.Render(ri.FilePath, ri.RenderTemplate, ri.Start, ri.Length);
if (status != RenderStatus.Complete)
{
ErrorLog(String.Format("{0} raised error {1}", ri.FilePath, status.ToString()));
}
else
{
// file successfully rendered
// strip padding
if (ri.RenderParams.GetParam <bool>(RenderTags.DoPadding))
{
WaveFile.StripPadding(ri.FilePath, ri.PaddingSeconds);
}
}
}
foreach (ScriptPortal.Vegas.Track trk in myVegas.Project.Tracks)
{
trk.Mute = false;
}
undo.Cancel = true; // we didn't really do anything useful.
}
}
/// <summary>
/// Initializes a new instance of the <see cref="T:NoobAudioLib.FX.Volume"/> class.
/// </summary>
/// <param name="waveFile">Wave file.</param>
public Volume(WaveFile waveFile)
{
this.waveFile = waveFile;
}
private IEnumerator ProcessChat()
{
if (source.isPlaying)
{
yield return(null);
}
while (processStatus != "Process")
{
yield return(null);
}
// When processing the chat, ignore input speech
if (processStatus == "Process")
{
speechStreamer.Active = false;
}
processStatus = "Processing";
if (String.IsNullOrEmpty(inputSpeech))
{
yield return(null);
}
messageTested = false;
var inputMessage = new MessageInput()
{
Text = inputSpeech,
Options = new MessageInputOptions()
{
ReturnContext = true
}
};
Assistant_service.Message(OnMessage, assistantId, sessionId, input: inputMessage);
while (!messageTested)
{
messageTested = false;
yield return(null);
}
//_testString = "I am Bob";
if (!String.IsNullOrEmpty(_testString))
{
byte[] synthesizeResponse = null;
AudioClip clip = null;
tts_service.Synthesize(
callback: (DetailedResponse <byte[]> response, IBMError error) =>
{
synthesizeResponse = response.Result;
clip = WaveFile.ParseWAV("myClip" + counter.ToString(), synthesizeResponse);
PlayClip(clip);
},
text: _testString,
//voice: "en-US_AllisonV3Voice",
voice: "en-US_MichaelV3Voice",
//voice: "en-US_MichaelVoice",
accept: "audio/wav"
);
while (synthesizeResponse == null)
{
yield return(null);
}
counter++;
// Set the flag to know that speech processing has finished
processStatus = "Finished";
yield return(new WaitForSeconds(clip.length));
}
}
public IEnumerator CreateService()
{
if (string.IsNullOrEmpty(Assistant_apikey))
{
throw new IBMException("Please provide Watson Assistant IAM ApiKey for the service.");
}
// Create credential and instantiate service
// IamAuthenticator authenticator = new IamAuthenticator(apikey: Assistant_apikey, url: serviceUrl);
IamAuthenticator authenticator = new IamAuthenticator(apikey: Assistant_apikey);
// Wait for tokendata
while (!authenticator.CanAuthenticate())
{
yield return(null);
}
Assistant_service = new AssistantService(versionDate, authenticator);
if (!string.IsNullOrEmpty(serviceUrl))
{
Assistant_service.SetServiceUrl(serviceUrl);
}
if (string.IsNullOrEmpty(tts_apikey))
{
throw new IBMException("Please provide Text-to-speech IAM ApiKey for the service.");
}
// Create credential and instantiate service
tts_authenticator = new IamAuthenticator(apikey: tts_apikey);
// Wait for tokendata
while (!tts_authenticator.CanAuthenticate())
{
yield return(null);
}
tts_service = new TextToSpeechService(tts_authenticator);
if (!string.IsNullOrEmpty(tts_serviceUrl))
{
tts_service.SetServiceUrl(tts_serviceUrl);
}
// Set speech processing status to "Processing"
processStatus = "Processing";
// Create services
Runnable.Run(speechStreamer.CreateService());
// Ignore input speech while the bot is speaking.
speechStreamer.Active = false;
Assistant_service.CreateSession(OnCreateSession, assistantId);
while (!createSessionTested)
{
yield return(null);
}
messageTested = false;
var inputMessage = new MessageInput()
{
Text = inputSpeech,
Options = new MessageInputOptions()
{
ReturnContext = true
}
};
Assistant_service.Message(OnMessage, assistantId, sessionId);
while (!messageTested)
{
messageTested = false;
yield return(null);
}
//_testString = "I am Bob";
// if (!String.IsNullOrEmpty(_testString))
// {
byte[] synthesizeResponse = null;
AudioClip clip = null;
tts_service.Synthesize(
callback: (DetailedResponse <byte[]> response, IBMError error) =>
{
synthesizeResponse = response.Result;
clip = WaveFile.ParseWAV("myClip" + counter.ToString(), synthesizeResponse);
PlayClip(clip);
},
text: _testString,
//voice: "en-US_AllisonV3Voice",
voice: "en-US_MichaelV3Voice",
//voice: "en-US_MichaelVoice",
accept: "audio/wav"
);
while (synthesizeResponse == null)
{
yield return(null);
}
counter++;
processStatus = "Finished";
yield return(new WaitForSeconds(clip.length));
// }
}
private void doExport()
{
if (!string.IsNullOrEmpty(FileName))
{
string wavFileName = FileName;
if (System.IO.Path.GetExtension(FileName).ToLowerInvariant() == ".ogg")
{
wavFileName =
System.IO.Path.Combine(
System.IO.Path.GetDirectoryName(FileName),
string.Format("{0}.wav", System.IO.Path.GetFileNameWithoutExtension(FileName))
);
}
WaveFile wav = new WaveFile(2, 16, 44100, wavFileName);
Player p = new Player();
p.Stereo = ApplicationState.Instance.Stereo;
p.NextLine += new Player.NextLineEventHandler(updateNextLine);
p.SongFinished += new EventHandler(songFinished);
p.CurrentSong = ApplicationState.Instance.CurrentSong;
p.DumpToWavFile(wav, NumRepeats);
wav.Close();
if(wavFileName != FileName)
{
convertToOgg(wavFileName);
}
this.Parent.NotifyCompleted();
}
}
//--Methods
public static float[] GetSampleDataInterleaved(WaveFile wave, int expectedChannels)
{
return GetSampleDataInterleaved(wave.Data.RawSampleData, wave.Format.BitsPerSample, wave.Format.ChannelCount, expectedChannels);
}
/// <summary>
/// Generates the specified dual-tone multi-frequency <paramref name="repeatCount"/> times storing it in the specified <see cref="WaveFile"/>.
/// </summary>
/// <param name="destination"><see cref="WaveFile"/> used to store generated dual-tone multi-frequencies.</param>
/// <param name="tone">Dual-tone multi-frequency to generate.</param>
/// <param name="volume">Volume of generated dual-tones as a percentage (0 to 1).</param>
/// <param name="repeatCount">Number of times to repeat the tone.</param>
public static void Generate(WaveFile destination, DTMF tone, double volume, int repeatCount)
{
Generate(destination, new DTMF[] { tone }, volume, repeatCount);
}
public void extractFeatures()
{
//NWaves
//Initial setup
if (_filePath != null)
{
DiscreteSignal signal;
// load
var mfcc_no = 24;
var samplingRate = 44100;
var mfccOptions = new MfccOptions
{
SamplingRate = samplingRate,
FeatureCount = mfcc_no,
FrameDuration = 0.025 /*sec*/,
HopDuration = 0.010 /*sec*/,
PreEmphasis = 0.97,
Window = WindowTypes.Hamming
};
var opts = new MultiFeatureOptions
{
SamplingRate = samplingRate,
FrameDuration = 0.025,
HopDuration = 0.010
};
var tdExtractor = new TimeDomainFeaturesExtractor(opts);
var mfccExtractor = new MfccExtractor(mfccOptions);
// Read from file.
featureString = String.Empty;
featureString = $"green,";
//MFCC
var avg_vec_mfcc = new List <float>(mfcc_no + 1);
//TD Features
var avg_vec_td = new List <float>(4);
//Spectral features
var avg_vec_spect = new List <float>(10);
for (var i = 0; i < mfcc_no; i++)
{
avg_vec_mfcc.Add(0f);
}
for (var i = 0; i < 4; i++)
{
avg_vec_td.Add(0f);
}
for (var i = 0; i < 10; i++)
{
avg_vec_spect.Add(0f);
}
string specFeatures = String.Empty;
Console.WriteLine($"{tag} Reading from file");
using (var stream = new FileStream(_filePath, FileMode.Open))
{
var waveFile = new WaveFile(stream);
signal = waveFile[channel : Channels.Left];
////Compute MFCC
float[] mfvfuck = new float[25];
var sig_sam = signal.Samples;
mfccVectors = mfccExtractor.ComputeFrom(sig_sam);
var fftSize = 1024;
tdVectors = tdExtractor.ComputeFrom(signal.Samples);
var fft = new Fft(fftSize);
var resolution = (float)samplingRate / fftSize;
var frequencies = Enumerable.Range(0, fftSize / 2 + 1)
.Select(f => f * resolution)
.ToArray();
var spectrum = new Fft(fftSize).MagnitudeSpectrum(signal).Samples;
var centroid = Spectral.Centroid(spectrum, frequencies);
var spread = Spectral.Spread(spectrum, frequencies);
var flatness = Spectral.Flatness(spectrum, 0);
var noiseness = Spectral.Noiseness(spectrum, frequencies, 3000);
var rolloff = Spectral.Rolloff(spectrum, frequencies, 0.85f);
var crest = Spectral.Crest(spectrum);
var decrease = Spectral.Decrease(spectrum);
var entropy = Spectral.Entropy(spectrum);
specFeatures = $"{centroid},{spread},{flatness},{noiseness},{rolloff},{crest},{decrease},{entropy}";
//}
Console.WriteLine($"{tag} All features ready");
for (int calibC = 0; calibC < mfccVectors.Count; calibC += (mfccVectors.Count / duration) - 1)
{
featureString = String.Empty;
var tmp = new ModelInput();
for (var i = 0; i < mfcc_no; i++)
{
avg_vec_mfcc[i] = mfccVectors[calibC][i];
}
for (var i = 0; i < 4; i++)
{
avg_vec_td[i] = tdVectors[calibC][i];
}
featureString += String.Join(",", avg_vec_mfcc);
featureString += ",";
featureString += String.Join(",", avg_vec_td);
featureString += ",";
featureString += specFeatures;
Console.WriteLine($"{tag} Feature String ready {featureString}");
if (File.Exists(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp")))
{
File.Delete(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp"));
File.WriteAllText(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp"), featureString);
}
else
{
File.WriteAllText(Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp"), featureString);
}
MLContext mLContext = new MLContext();
string fileName = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "temp");
IDataView dataView = mLContext.Data.LoadFromTextFile <ModelInput>(
path: fileName,
hasHeader: false,
separatorChar: ',',
allowQuoting: true,
allowSparse: false);
// Use first line of dataset as model input
// You can replace this with new test data (hardcoded or from end-user application)
ModelInput sampleForPrediction = mLContext.Data.CreateEnumerable <ModelInput>(dataView, false)
.First();
ModelOutput opm = ConsumeModel.Predict(sampleForPrediction);
featureTimeList.Add(opm.Score);
Console.WriteLine($"{tag} Feature vs time list ready");
}
//Console.WriteLine($"{tag} MFCC: {mfccVectors.Count}");
//Console.WriteLine($"{tag} TD: {tdVectors.Count}");
//Console.WriteLine($"{tag} featureTimeArray: {featureTimeList.Count} {featureString}");
}
}
}
/// <summary>
/// Initializes a new instance of the <see cref="T:NoobAudioLib.FX.PitchShift"/> class.
/// </summary>
/// <param name="SampleRate">Sample rate.</param>
/// <param name="waveFile">Wave file.</param>
public PitchShift(int SampleRate, WaveFile waveFile, int pitchModifier)
{
this.waveFile = waveFile;
this.SampleRate = SampleRate;
}
private void openToolStripMenuItem_Click(object sender, EventArgs e)
{
var ofd = new OpenFileDialog();
if (ofd.ShowDialog() != DialogResult.OK)
{
return;
}
using (var stream = new FileStream(ofd.FileName, FileMode.Open))
{
var waveFile = new WaveFile(stream);
_signal = waveFile[Channels.Left];
}
_stft = new Stft(_frameSize, _hopSize);
var frameDuration = (double)_frameSize / _signal.SamplingRate;
var hopDuration = (double)_hopSize / _signal.SamplingRate;
var freqs = new[] { 300f, 600, 1000, 2000, 4000, 7000 };
var pitchOptions = new PitchOptions
{
SamplingRate = _signal.SamplingRate,
FrameDuration = frameDuration,
HopDuration = hopDuration,
HighFrequency = 900/*Hz*/
};
var pitchExtractor = new PitchExtractor(pitchOptions);
var pitchTrack = pitchExtractor.ParallelComputeFrom(_signal)
.Select(p => p[0])
.ToArray();
var options = new MultiFeatureOptions
{
SamplingRate = _signal.SamplingRate,
FrameDuration = frameDuration,
HopDuration = hopDuration
};
var tdExtractor = new TimeDomainFeaturesExtractor(options);
tdExtractor.AddFeature("pitch_zcr", (signal, start, end) => Pitch.FromZeroCrossingsSchmitt(signal, start, end));
var mpeg7Extractor = new Mpeg7SpectralFeaturesExtractor(options);
mpeg7Extractor.IncludeHarmonicFeatures("all");
mpeg7Extractor.SetPitchTrack(pitchTrack);
options.FeatureList = "sc+sn";
options.Frequencies = freqs;
var spectralExtractor = new SpectralFeaturesExtractor(options);
//spectralExtractor.AddFeature("pitch_hss", (spectrum, fs) => Pitch.FromHss(spectrum, _signal.SamplingRate));
var tdVectors = tdExtractor.ParallelComputeFrom(_signal);
var spectralVectors = spectralExtractor.ParallelComputeFrom(_signal);
var mpeg7Vectors = mpeg7Extractor.ComputeFrom(_signal);
_vectors = FeaturePostProcessing.Join(tdVectors, spectralVectors, mpeg7Vectors);
//FeaturePostProcessing.NormalizeMean(_vectors);
//FeaturePostProcessing.AddDeltas(_vectors);
var descriptions = tdExtractor.FeatureDescriptions
.Concat(spectralExtractor.FeatureDescriptions)
.Concat(mpeg7Extractor.FeatureDescriptions)
.ToList();
FillFeaturesList(_vectors, descriptions, tdExtractor.TimeMarkers(_vectors.Length));
spectrogramPlot.ColorMapName = "afmhot";
spectrogramPlot.MarklineThickness = 2;
spectrogramPlot.Spectrogram = _stft.Spectrogram(_signal);
}
/// <summary>
/// Initializes a new instance of the <see cref="T:NoobAudioLib.FX.Reverb"/> class.
/// </summary>
/// <param name="waveFile">Wave file.</param>
/// <param name="DelayMS">Delay in miliseconds.</param>
/// <param name="Decay">Decay.</param>
public Reverb(WaveFile waveFile, int DelayMS, float Decay)
{
this.DelayMS = DelayMS;
this.Decay = Decay;
this.waveFile = waveFile;
}
public Reverse(WaveFile waveFile)
{
this.waveFile = waveFile;
}
/// <summary>
/// Initializes a new instance of the <see cref="T:NoobAudioLib.FX.Trimmer"/> class.
/// </summary>
/// <param name="SampleRate">Sample rate.</param>
/// <param name="waveFile">Wave file.</param>
public Trimmer(int SampleRate, WaveFile waveFile)
{
this.waveFile = waveFile;
this.SampleRate = SampleRate;
}
private void OnDragDrop(object sender, DragEventArgs e)
{
string[] files = (string[])e.Data.GetData(DataFormats.FileDrop);
WaveFile f = new WaveFile();
foreach (string file in files)
{
f = WaveManagerBusiness.WaveManager.OpenFile(file);
}
}
/// <summary>
/// Initializes a new instance of the <see cref="T:NoobAudioLib.FX.SpeedShift"/> class.
/// </summary>
/// <param name="waveFile">Wave file.</param>
public SpeedShift(WaveFile waveFile)
{
this.waveFile = waveFile;
}
private void UpdateToolbarOptionsForCurrentWindow(WaveFile file)
{
UpdateToolbarOptionsForCurrentWindow();
}
public void WriteBuffer(byte[] buff, WaveFormatEx wfex, string destFile)
{
WaveFile.WriteWaveData(buff, wfex, destFile);
}
/// <summary>
/// Generates the specified dual-tone multi-frequency storing it in the specified <see cref="WaveFile"/>.
/// </summary>
/// <param name="destination"><see cref="WaveFile"/> used to store generated dual-tone multi-frequencies.</param>
/// <param name="tone">Dual-tone multi-frequency to generate.</param>
/// <param name="volume">Volume of generated dual-tones as a percentage (0 to 1).</param>
public static void Generate(WaveFile destination, DTMF tone, double volume)
{
Generate(destination, new[] { tone }, volume, 1);
}
/// <summary>
/// Create an instance of WaveIn.
/// </summary>
public WaveIn()
{
m_msgWindow = new SoundMessageWindow(this);
m_file = new WaveFile();
}
/// <summary>
/// Generates the specified dual-tone multi-frequency <paramref name="repeatCount"/> times storing it in the specified <see cref="WaveFile"/>.
/// </summary>
/// <param name="destination"><see cref="WaveFile"/> used to store generated dual-tone multi-frequencies.</param>
/// <param name="tone">Dual-tone multi-frequency to generate.</param>
/// <param name="volume">Volume of generated dual-tones as a percentage (0 to 1).</param>
/// <param name="repeatCount">Number of times to repeat the tone.</param>
public static void Generate(WaveFile destination, DTMF tone, double volume, int repeatCount)
{
Generate(destination, new[] { tone }, volume, repeatCount);
}
public ParticleVacuumEffect(ParticleSystem particleSystem, Transform vacuumTarget, WaveFile audioBuffer, float deletionDistance)
{
_particleSystem = particleSystem;
_vacuumTarget = vacuumTarget;
_waveFile = audioBuffer;
DeletionDistance = deletionDistance;
_particleSystem.ModifyAllParticles((ref ParticleState ps) =>
{
Vector3 direction = Vector3.Normalize(ps.Offset - _vacuumTarget.Position);
ps.Velocity += (ps.Offset - _particleSystem.Transform.Position) * InitialExpulsionVelocity;
});
}
/// <summary>
/// Generates a single instance of each of the specified dual-tone multi-frequencies storing them in the specified <see cref="WaveFile"/>.
/// </summary>
/// <param name="destination"><see cref="WaveFile"/> used to store generated dual-tone multi-frequencies.</param>
/// <param name="tones">Dual-tone multi-frequencies to generate.</param>
/// <param name="volume">Volume of generated dual-tones as a percentage (0 to 1).</param>
public static void Generate(WaveFile destination, DTMF[] tones, double volume)
{
Generate(destination, tones, volume, 1);
}
public void DoTranscoding(EncoderSettings encoderSettings, string inputFile)
{
_grabber = CdRipper.CreateGrabber(OutputFormat);
if (_grabber == null)
{
throw new NotSupportedException(string.Format("TXT_UNSUPPORTED_OUTPUT_FORMAT: {0}", InputFormat));
}
switch (InputFormat)
{
case AudioMediaFormatType.WAV:
switch (OutputFormat)
{
case AudioMediaFormatType.MP3:
{
// Transcode WAV => MP3 i.o.w encode the wav
WaveFormatEx wfex = WaveFormatEx.Cdda;
byte[] buff = WaveFile.ReadWaveData(inputFile, ref wfex);
GrabberToMP3 grabber = (_grabber as GrabberToMP3);
grabber.Options = (encoderSettings as Mp3EncoderSettings).Options;
// Resample is not supported at this time.
// Specify the same settings as the input WAV file, otherwise we'll be failing.
grabber.Options.WaveFormat = wfex;
grabber.EncodeBuffer(buff,
Path.ChangeExtension(inputFile, "MP3"),
false, null);
return;
}
}
break;
case AudioMediaFormatType.MP3:
switch (OutputFormat)
{
case AudioMediaFormatType.WAV:
// Transcode MP3 => WAV i.o.w decode the MP3
string outputFile = Path.ChangeExtension(inputFile, "WAV");
if (DecodeMP3ToWAV(inputFile, outputFile) == false)
{
throw new Exception("TXT_FAILED_CONVERSION_MP3_WAV");
}
return;
case AudioMediaFormatType.MP3:
{
// Transcode MP3 => MP3 i.o.w adjust MP3 encoding
string tempWavFile = Path.GetTempFileName();
if (DecodeMP3ToWAV(inputFile, tempWavFile) == false)
{
throw new Exception("TXT_FAILED_CONVERSION_MP3_TEMP_WAV");
}
WaveFormatEx wfex = WaveFormatEx.Cdda;
byte[] buff = WaveFile.ReadWaveData(tempWavFile, ref wfex);
GrabberToMP3 grabber = (_grabber as GrabberToMP3);
grabber.Options = (encoderSettings as Mp3EncoderSettings).Options;
ID3FileInfoSlim ifiSlim =
new ID3FileInfoSlim(MediaFileInfo.FromPath(inputFile, false));
grabber.EncodeBuffer(buff,
Path.ChangeExtension(inputFile, "REENC.MP3"),
(encoderSettings as Mp3EncoderSettings).CopyInputFileMetadata,
ifiSlim);
if (File.Exists(tempWavFile))
{
File.Delete(tempWavFile);
}
return;
}
}
break;
}
throw new NotSupportedException(string.Format("TXT_UNSUPPORTED_TRANSCODING: {0}", this));
}
public override IEnumerator RunTest()
{
LogSystem.InstallDefaultReactors();
try
{
VcapCredentials vcapCredentials = new VcapCredentials();
fsData data = null;
// Get credentials from a credential file defined in environmental variables in the VCAP_SERVICES format.
// See https://www.ibm.com/watson/developercloud/doc/common/getting-started-variables.html.
var environmentalVariable = Environment.GetEnvironmentVariable("VCAP_SERVICES");
var fileContent = File.ReadAllText(environmentalVariable);
// Add in a parent object because Unity does not like to deserialize root level collection types.
fileContent = Utility.AddTopLevelObjectToJson(fileContent, "VCAP_SERVICES");
// Convert json to fsResult
fsResult r = fsJsonParser.Parse(fileContent, out data);
if (!r.Succeeded)
{
throw new WatsonException(r.FormattedMessages);
}
// Convert fsResult to VcapCredentials
object obj = vcapCredentials;
r = _serializer.TryDeserialize(data, obj.GetType(), ref obj);
if (!r.Succeeded)
{
throw new WatsonException(r.FormattedMessages);
}
// Set credentials from imported credntials
Credential credential = vcapCredentials.VCAP_SERVICES["speech_to_text"][TestCredentialIndex].Credentials;
_username = credential.Username.ToString();
_password = credential.Password.ToString();
_url = credential.Url.ToString();
}
catch
{
Log.Debug("TestSpeechToText", "Failed to get credentials from VCAP_SERVICES file. Please configure credentials to run this test. For more information, see: https://github.com/watson-developer-cloud/unity-sdk/#authentication");
}
// Create credential and instantiate service
Credentials credentials = new Credentials(_username, _password, _url);
// Or authenticate using token
//Credentials credentials = new Credentials(_url)
//{
// AuthenticationToken = _token
//};
_speechToText = new SpeechToText(credentials);
_customCorpusFilePath = Application.dataPath + "/Watson/Examples/ServiceExamples/TestData/test-stt-corpus.txt";
_customWordsFilePath = Application.dataPath + "/Watson/Examples/ServiceExamples/TestData/test-stt-words.json";
_wavFilePath = Application.dataPath + "/Watson/Examples/ServiceExamples/TestData/test-audio.wav";
_audioClip = WaveFile.ParseWAV("testClip", File.ReadAllBytes(_wavFilePath));
Log.Debug("ExampleSpeechToText", "Attempting to recognize");
_speechToText.Recognize(_audioClip, HandleOnRecognize);
while (!_recognizeTested)
{
yield return(null);
}
// Get models
Log.Debug("ExampleSpeechToText", "Attempting to get models");
_speechToText.GetModels(HandleGetModels);
while (!_getModelsTested)
{
yield return(null);
}
// Get model
Log.Debug("ExampleSpeechToText", "Attempting to get model {0}", _modelNameToGet);
_speechToText.GetModel(HandleGetModel, _modelNameToGet);
while (!_getModelTested)
{
yield return(null);
}
// Get customizations
Log.Debug("ExampleSpeechToText", "Attempting to get customizations");
_speechToText.GetCustomizations(HandleGetCustomizations);
while (!_getCustomizationsTested)
{
yield return(null);
}
// Create customization
Log.Debug("ExampleSpeechToText", "Attempting create customization");
_speechToText.CreateCustomization(HandleCreateCustomization, "unity-test-customization", "en-US_BroadbandModel", "Testing customization unity");
while (!_createCustomizationsTested)
{
yield return(null);
}
// Get customization
Log.Debug("ExampleSpeechToText", "Attempting to get customization {0}", _createdCustomizationID);
_speechToText.GetCustomization(HandleGetCustomization, _createdCustomizationID);
while (!_getCustomizationTested)
{
yield return(null);
}
// Get custom corpora
Log.Debug("ExampleSpeechToText", "Attempting to get custom corpora for {0}", _createdCustomizationID);
_speechToText.GetCustomCorpora(HandleGetCustomCorpora, _createdCustomizationID);
while (!_getCustomCorporaTested)
{
yield return(null);
}
// Add custom corpus
Log.Debug("ExampleSpeechToText", "Attempting to add custom corpus {1} in customization {0}", _createdCustomizationID, _createdCorpusName);
_speechToText.AddCustomCorpus(HandleAddCustomCorpus, _createdCustomizationID, _createdCorpusName, true, _customCorpusFilePath);
while (!_addCustomCorpusTested)
{
yield return(null);
}
// Get custom corpus
Log.Debug("ExampleSpeechToText", "Attempting to get custom corpus {1} in customization {0}", _createdCustomizationID, _createdCorpusName);
_speechToText.GetCustomCorpus(HandleGetCustomCorpus, _createdCustomizationID, _createdCorpusName);
while (!_getCustomCorpusTested)
{
yield return(null);
}
// Wait for customization
Runnable.Run(CheckCustomizationStatus(_createdCustomizationID));
while (!_isCustomizationReady)
{
yield return(null);
}
// Get custom words
Log.Debug("ExampleSpeechToText", "Attempting to get custom words.");
_speechToText.GetCustomWords(HandleGetCustomWords, _createdCustomizationID);
while (!_getCustomWordsTested)
{
yield return(null);
}
// Add custom words from path
Log.Debug("ExampleSpeechToText", "Attempting to add custom words in customization {0} using Words json path {1}", _createdCustomizationID, _customWordsFilePath);
string customWords = File.ReadAllText(_customWordsFilePath);
_speechToText.AddCustomWords(HandleAddCustomWordsFromPath, _createdCustomizationID, customWords);
while (!_addCustomWordsFromPathTested)
{
yield return(null);
}
// Wait for customization
_isCustomizationReady = false;
Runnable.Run(CheckCustomizationStatus(_createdCustomizationID));
while (!_isCustomizationReady)
{
yield return(null);
}
// Add custom words from object
Words words = new Words();
Word w0 = new Word();
List <Word> wordList = new List <Word>();
w0.word = "mikey";
w0.sounds_like = new string[1];
w0.sounds_like[0] = "my key";
w0.display_as = "Mikey";
wordList.Add(w0);
Word w1 = new Word();
w1.word = "charlie";
w1.sounds_like = new string[1];
w1.sounds_like[0] = "char lee";
w1.display_as = "Charlie";
wordList.Add(w1);
Word w2 = new Word();
w2.word = "bijou";
w2.sounds_like = new string[1];
w2.sounds_like[0] = "be joo";
w2.display_as = "Bijou";
wordList.Add(w2);
words.words = wordList.ToArray();
Log.Debug("ExampleSpeechToText", "Attempting to add custom words in customization {0} using Words object", _createdCustomizationID);
_speechToText.AddCustomWords(HandleAddCustomWordsFromObject, _createdCustomizationID, words);
while (!_addCustomWordsFromObjectTested)
{
yield return(null);
}
// Wait for customization
_isCustomizationReady = false;
Runnable.Run(CheckCustomizationStatus(_createdCustomizationID));
while (!_isCustomizationReady)
{
yield return(null);
}
// Get custom word
Log.Debug("ExampleSpeechToText", "Attempting to get custom word {1} in customization {0}", _createdCustomizationID, words.words[0].word);
_speechToText.GetCustomWord(HandleGetCustomWord, _createdCustomizationID, words.words[0].word);
while (!_getCustomWordTested)
{
yield return(null);
}
// Train customization
Log.Debug("ExampleSpeechToText", "Attempting to train customization {0}", _createdCustomizationID);
_speechToText.TrainCustomization(HandleTrainCustomization, _createdCustomizationID);
while (!_trainCustomizationTested)
{
yield return(null);
}
// Wait for customization
_isCustomizationReady = false;
Runnable.Run(CheckCustomizationStatus(_createdCustomizationID));
while (!_isCustomizationReady)
{
yield return(null);
}
// Upgrade customization - not currently implemented in service
//Log.Debug("ExampleSpeechToText", "Attempting to upgrade customization {0}", _createdCustomizationID);
//_speechToText.UpgradeCustomization(HandleUpgradeCustomization, _createdCustomizationID);
//while (!_upgradeCustomizationTested)
// yield return null;
// Delete custom word
Log.Debug("ExampleSpeechToText", "Attempting to delete custom word {1} in customization {0}", _createdCustomizationID, words.words[2].word);
_speechToText.DeleteCustomWord(HandleDeleteCustomWord, _createdCustomizationID, words.words[2].word);
while (!_deleteCustomWordTested)
{
yield return(null);
}
// Delay
Log.Debug("ExampleDiscovery", string.Format("Delaying delete environment for {0} sec", _delayTimeInSeconds));
Runnable.Run(Delay(_delayTimeInSeconds));
while (!_readyToContinue)
{
yield return(null);
}
_readyToContinue = false;
// Delete custom corpus
Log.Debug("ExampleSpeechToText", "Attempting to delete custom corpus {1} in customization {0}", _createdCustomizationID, _createdCorpusName);
_speechToText.DeleteCustomCorpus(HandleDeleteCustomCorpus, _createdCustomizationID, _createdCorpusName);
while (!_deleteCustomCorpusTested)
{
yield return(null);
}
// Delay
Log.Debug("ExampleDiscovery", string.Format("Delaying delete environment for {0} sec", _delayTimeInSeconds));
Runnable.Run(Delay(_delayTimeInSeconds));
while (!_readyToContinue)
{
yield return(null);
}
_readyToContinue = false;
// Reset customization
Log.Debug("ExampleSpeechToText", "Attempting to reset customization {0}", _createdCustomizationID);
_speechToText.ResetCustomization(HandleResetCustomization, _createdCustomizationID);
while (!_resetCustomizationTested)
{
yield return(null);
}
// Delay
Log.Debug("ExampleDiscovery", string.Format("Delaying delete environment for {0} sec", _delayTimeInSeconds));
Runnable.Run(Delay(_delayTimeInSeconds));
while (!_readyToContinue)
{
yield return(null);
}
_readyToContinue = false;
// Delete customization
Log.Debug("ExampleSpeechToText", "Attempting to delete customization {0}", _createdCustomizationID);
_speechToText.DeleteCustomization(HandleDeleteCustomization, _createdCustomizationID);
while (!_deleteCustomizationsTested)
{
yield return(null);
}
Log.Debug("ExampleSpeechToText", "Speech to Text examples complete.");
yield break;
}
/// <summary>
/// Create an instance of WaveOut.
/// </summary>
public WaveOut()
{
m_msgWindow = new SoundMessageWindow(this);
m_file = new WaveFile();
}
private void openToolStripMenuItem_Click(object sender, EventArgs e)
{
var ofd = new OpenFileDialog();
if (ofd.ShowDialog() != DialogResult.OK)
{
return;
}
_waveFileName = ofd.FileName;
using (var stream = new FileStream(_waveFileName, FileMode.Open))
{
var waveFile = new WaveFile(stream);
_bitDepth = waveFile.WaveFmt.BitsPerSample;
_signal = waveFile[Channels.Average];
}
_stft = new Stft(512, 64, _windowType);
_spectrogram = _stft.Spectrogram(_signal);
//var processed = _stft.Inverse(_stft.Direct(_signal));
//_processedSignal = new DiscreteSignal(_signal.SamplingRate, processed);
// 1) check also this:
var mp = _stft.MagnitudePhaseSpectrogram(_signal);
var processed = _stft.ReconstructMagnitudePhase(mp);
_processedSignal = new DiscreteSignal(_signal.SamplingRate, processed);
// 2) or check this:
//var processed = new GriffinLimReconstructor(_spectrogram, _stft).Reconstruct();
//_processedSignal = new DiscreteSignal(_signal.SamplingRate, processed);
signalPanel.Gain = 120;
signalPanel.Signal = _signal;
processedSignalPanel.Gain = 120;
processedSignalPanel.Signal = _processedSignal;
spectrogramPanel.Spectrogram = _spectrogram;
//// StftC - has complex FFT
//// RealFFT-based Stft is 30% faster!
//var sr = new Stft(2048, 256);
//var sc = new StftC(2048, 256);
//var sw = new Stopwatch();
//sw.Start();
//for (var i = 0; i < 10; i++)
//{
// var processed1 = sr.Inverse(sr.Direct(_signal));
// _processedSignal = new DiscreteSignal(_signal.SamplingRate, processed1);
//}
//sw.Stop();
//var t1 = sw.Elapsed;
//sw.Reset();
//sw.Start();
//for (var i = 0; i < 10; i++)
//{
// var processed1 = sc.Inverse(sc.Direct(_signal));
// _processedSignal = new DiscreteSignal(_signal.SamplingRate, processed1);
//}
//sw.Stop();
//var t2 = sw.Elapsed;
//MessageBox.Show(t1 + " " + t2);
}
/// <summary>
/// Generates the specified dual-tone multi-frequency storing it in the specified <see cref="WaveFile"/>.
/// </summary>
/// <param name="destination"><see cref="WaveFile"/> used to store generated dual-tone multi-frequencies.</param>
/// <param name="tone">Dual-tone multi-frequency to generate.</param>
/// <param name="volume">Volume of generated dual-tones as a percentage (0 to 1).</param>
public static void Generate(WaveFile destination, DTMF tone, double volume)
{
Generate(destination, new DTMF[] { tone }, volume, 1);
}
static int Main(string[] args)
{
// System settings
ConfigurationFile configFile = ConfigurationFile.Current;
CategorizedSettingsElementCollection systemSettings = configFile.Settings["systemSettings"];
systemSettings.Add("NodeID", Guid.NewGuid().ToString(), "Unique Node ID");
Guid nodeID = systemSettings["NodeID"].ValueAs <Guid>();
bool useMemoryCache = systemSettings["UseMemoryCache"].ValueAsBoolean(false);
string connectionString = systemSettings["ConnectionString"].Value;
string nodeIDQueryString = null;
string parameterizedQuery;
int protocolID, signalTypePMID, signalTypePAID;
// Define guid with query string delimiters according to database needs
Dictionary <string, string> settings = connectionString.ParseKeyValuePairs();
string setting;
if (settings.TryGetValue("Provider", out setting))
{
// Check if provider is for Access since it uses braces as Guid delimiters
if (setting.StartsWith("Microsoft.Jet.OLEDB", StringComparison.OrdinalIgnoreCase))
{
nodeIDQueryString = "{" + nodeID + "}";
}
}
if (string.IsNullOrWhiteSpace(nodeIDQueryString))
{
nodeIDQueryString = "'" + nodeID + "'";
}
using (AdoDataConnection database = new AdoDataConnection("systemSettings"))
{
IDbConnection connection = database.Connection;
if (Convert.ToInt32(connection.ExecuteScalar("SELECT COUNT(*) FROM Protocol WHERE Acronym='WAV'")) == 0)
{
if (database.IsSQLServer || database.IsJetEngine)
{
connection.ExecuteNonQuery("INSERT INTO Protocol(Acronym, Name, [Type], Category, AssemblyName, TypeName) VALUES('WAV', 'Wave Form Input Adapter', 'Frame', 'Audio', 'WavInputAdapter.dll', 'WavInputAdapter.WavInputAdapter')");
}
else
{
connection.ExecuteNonQuery("INSERT INTO Protocol(Acronym, Name, Type, Category, AssemblyName, TypeName) VALUES('WAV', 'Wave Form Input Adapter', 'Frame', 'Audio', 'WavInputAdapter.dll', 'WavInputAdapter.WavInputAdapter')");
}
}
protocolID = Convert.ToInt32(connection.ExecuteScalar("SELECT ID FROM Protocol WHERE Acronym='WAV'"));
// Typically these values should be defined as analogs, however, we use a voltage magnitude signal type
// since these types of values can be better graphed with auto-scaling in the visualization tools
signalTypePMID = Convert.ToInt32(connection.ExecuteScalar("SELECT ID FROM SignalType WHERE Acronym='VPHM'"));
signalTypePAID = Convert.ToInt32(connection.ExecuteScalar("SELECT ID FROM SignalType WHERE Acronym='VPHA'"));
string pathRoot = FilePath.GetDirectoryName((args.Length > 0) ? args[0] : systemSettings["MusicDirectory"].Value);
string sourcePath = Path.Combine(pathRoot, "*" + Path.DirectorySeparatorChar + "*.wav");
foreach (string sourceFileName in FilePath.GetFileList(sourcePath))
{
WaveFile sourceWave;
string fileName = FilePath.GetFileName(sourceFileName);
char[] invalidChars = { '\'', '[', ']', '(', ')', ',', '-', '.' };
Console.WriteLine("Loading metadata for \"{0}\"...\r\n", fileName);
sourceWave = WaveFile.Load(sourceFileName, false);
fileName = FilePath.GetFileNameWithoutExtension(fileName).RemoveDuplicateWhiteSpace().RemoveCharacters(invalidChars.Contains).Trim();
string acronym = fileName.Replace(' ', '_').ToUpper() + "_" + (int)(sourceWave.SampleRate / SI.Kilo) + "KHZ";
string name = GenerateSongName(sourceWave, fileName);
Console.WriteLine(" Acronym = {0}", acronym);
Console.WriteLine(" Name = {0}", name);
Console.WriteLine("");
// Check to see if device exists
if (Convert.ToInt32(connection.ExecuteScalar(database.ParameterizedQueryString("SELECT COUNT(*) FROM Device WHERE Acronym = {0}", "acronym"), acronym)) == 0)
{
parameterizedQuery = database.ParameterizedQueryString("INSERT INTO Device(NodeID, Acronym, Name, ProtocolID, FramesPerSecond, " +
"MeasurementReportingInterval, ConnectionString, Enabled) VALUES(" + nodeIDQueryString + ", {0}, {1}, {2}, {3}, {4}, {5}, {6})",
"acronym", "name", "protocolID", "framesPerSecond", "measurementReportingInterval",
"connectionString", "enabled");
// Insert new device record
connection.ExecuteNonQuery(parameterizedQuery, acronym, name, protocolID, sourceWave.SampleRate, 1000000, $"wavFileName={FilePath.GetAbsolutePath(sourceFileName)}; connectOnDemand=true; outputSourceIDs={acronym}; memoryCache={useMemoryCache}", database.Bool(true));
int deviceID = Convert.ToInt32(connection.ExecuteScalar(database.ParameterizedQueryString("SELECT ID FROM Device WHERE Acronym = {0}", "acronym"), acronym));
string pointTag;
int lastPhasorIndex = 0;
int phasorIndex = 1;
// Add a measurement for each defined wave channel
for (int i = 0; i < sourceWave.Channels; i++)
{
int index = i + 1;
int signalTypeID = index % 2 == 0 ? signalTypePAID : signalTypePMID;
if (i > 0 && i % 2 == 0)
{
phasorIndex++;
}
if (lastPhasorIndex != phasorIndex)
{
lastPhasorIndex = phasorIndex;
parameterizedQuery = database.ParameterizedQueryString("INSERT INTO Phasor(DeviceID, Label, Type, Phase, SourceIndex) VALUES ({0}, {1}, 'V', '+', {2})", "deviceID", "label", "sourceIndex");
// Insert new phasor record
connection.ExecuteNonQuery(parameterizedQuery, (object)deviceID, acronym, phasorIndex);
}
string signalSuffix = index % 2 == 0 ? "-PA" : "-PM";
pointTag = acronym + ":WAVA" + index;
parameterizedQuery = database.ParameterizedQueryString("INSERT INTO Measurement(DeviceID, PointTag, SignalTypeID, PhasorSourceIndex, SignalReference, Description, " +
"Enabled) VALUES({0}, {1}, {2}, {3}, {4}, {5}, {6})", "deviceID", "pointTag", "signalTypeID", "phasorSourceIndex", "signalReference", "description", "enabled");
// Insert new measurement record
connection.ExecuteNonQuery(parameterizedQuery, (object)deviceID, pointTag, signalTypeID, phasorIndex, acronym + signalSuffix + phasorIndex, name + " - channel " + phasorIndex, database.Bool(true));
//Convert.ToInt32(connection.ExecuteScalar(database.ParameterizedQueryString("SELECT PointID FROM Measurement WHERE PointTag = {0}", "pointTag"), pointTag));
}
// Disable all non analog measurements that may be associated with this device
connection.ExecuteNonQuery(database.ParameterizedQueryString("UPDATE Measurement SET Enabled = {0} WHERE DeviceID = {1} AND NOT SignalTypeID IN ({2}, {3})", "enabled", "deviceID", "signalTypePAID", "signalTypePMID"), database.Bool(false), deviceID, signalTypePAID, signalTypePMID);
}
}
}
return(0);
}
/// <summary>
/// Generates a single instance of each of the specified dual-tone multi-frequencies storing them in the specified <see cref="WaveFile"/>.
/// </summary>
/// <param name="destination"><see cref="WaveFile"/> used to store generated dual-tone multi-frequencies.</param>
/// <param name="tones">Dual-tone multi-frequencies to generate.</param>
/// <param name="volume">Volume of generated dual-tones as a percentage (0 to 1).</param>
public static void Generate(WaveFile destination, DTMF[] tones, double volume)
{
Generate(destination, tones, volume, 1);
}
public Delay(WaveFile waveFile)
{
this.waveFile = waveFile;
sampleRate = (int)this.waveFile.Format.SamplesPerSec;
}
/// <summary>
/// Combines wave files together, all starting at the same time, into a single file.
/// This has the effect of playing two sound tracks simultaneously.
/// </summary>
/// <param name="waveFiles">Wave files to combine</param>
/// <param name="volumes">Volume for each wave file (0.0 to 1.0)</param>
/// <returns>Combined wave files.</returns>
/// <remarks>
/// <para>
/// Cumulatively, volumes cannot exceed 1.0 - these volumes represent a fractional percentage
/// of volume to be applied to each wave file.
/// </para>
/// <para>
/// Resulting sounds will overlap; no truncation is performed. Final wave file length will equal length of
/// longest source file.
/// </para>
/// <para>
/// Combining sounds files with non-PCM based audio formats will have unexpected results.
/// </para>
/// </remarks>
public static WaveFile Combine(WaveFile[] waveFiles, double[] volumes)
{
if (waveFiles.Length > 1)
{
// Validate volumes
if (volumes.Length != waveFiles.Length)
throw new ArgumentOutOfRangeException("volumes", "There must be one volume per each wave file");
if (volumes.Sum() > 1.0D)
throw new ArgumentOutOfRangeException("volumes", "Cumulatively, volumes cannot exceed 1.0");
// Deep clone first wave file - this will become the base of the new combined wave file
WaveFile next, source = waveFiles[0].Clone();
int maxLength, nextLength, sourceLength = source.SampleBlocks.Count;
// Validate compatibility of wave files to be combined
for (int x = 1; x < waveFiles.Length; x++)
{
next = waveFiles[x];
if (source.AudioFormat != next.AudioFormat ||
source.SampleRate != next.SampleRate ||
source.BitsPerSample != next.BitsPerSample ||
source.Channels != next.Channels)
throw new ArgumentException("All wave files to be combined must have the same audio format, sample rate, bits per sample and number of channels");
}
// Apply volume adjustment to source file
for (int x = 0; x < sourceLength; x++)
{
for (int y = 0; y < source.Channels; y++)
{
// Apply volume adjustment to source
source.SampleBlocks[x][y] = CombineBinarySamples(source.BitsPerSample, 0, source.SampleBlocks[x][y], volumes[0]);
}
}
// Combine subsequent wave files
for (int x = 1; x < waveFiles.Length; x++)
{
next = waveFiles[x];
nextLength = next.SampleBlocks.Count;
maxLength = sourceLength > nextLength ? sourceLength : nextLength;
for (int y = 0; y < maxLength; y++)
{
if (y < sourceLength && y < nextLength)
{
for (int z = 0; z < source.Channels; z++)
{
// Combine each data channel from the source and current wave files
source.SampleBlocks[y][z] = CombineBinarySamples(source.BitsPerSample, source.SampleBlocks[y][z], next.SampleBlocks[y][z], volumes[x]);
}
}
else
{
// Extend source if necessary - note that extended samples still need to be equalized
if (nextLength > sourceLength)
{
LittleBinaryValue[] samples = new LittleBinaryValue[source.Channels];
for (int z = 0; z < source.Channels; z++)
{
// Combine extended samples with "0" from source to maintain amplitude equalization
samples[z] = CombineBinarySamples(source.BitsPerSample, 0, next.SampleBlocks[y][z], volumes[x]);
}
source.SampleBlocks.Add(samples);
}
else
break;
}
}
}
return source;
}
else
throw new ArgumentException("You must provide at least two wave files to combine.", "waveFiles");
}
public void ReadMainFileHeader()
{
waveFile = new WaveFile();
waveFile.maindata = new RiffChunk();
Debug.WriteLine("position reader: " + reader.BaseStream.Position);
waveFile.maindata.sGroupID = new string(reader.ReadChars(4));
Debug.WriteLine("position reader: " + reader.BaseStream.Position);
waveFile.maindata.dwFileLength = reader.ReadUInt32() + 8;
Debug.WriteLine("position reader: " + reader.BaseStream.Position);
waveFile.maindata.sRiffType = new string(reader.ReadChars(4));
Debug.WriteLine("position reader: " + reader.BaseStream.Position);
Debug.WriteLine(waveFile.maindata.dwFileLength);
Debug.WriteLine(reader.BaseStream.Length);
}