/**
* /// Decodes the batch of audio files
*/
public void decode(String batchFile)
{
BatchItem batchItem;
int count = 0;
try {
recognizer.Allocate();
setBatchFile(batchFile);
batchManager.Start();
this.LogInfo("BatchDecoder: decoding files in "
+ batchManager.Filename);
while (count < utteranceId &&
(batchItem = batchManager.GetNextItem()) != null)
{
setInputStream(batchItem.Filename);
Result result = recognizer.Recognize(batchItem.Transcript);
this.LogInfo("File : " + batchItem.Filename);
this.LogInfo("Result: " + result);
count++;
}
batchManager.Stop();
recognizer.Deallocate();
} catch (IOException io)
{
this.LogInfo("I/O error during decoding: " + io.Message);
throw io;
}
this.LogInfo("BatchDecoder: " + count + " files decoded");
}
/// <summary>
/// Starts recognition process.
/// </summary>
/// <param name="stream"></param>
/// <param name="timeFrame"></param>
public void StartRecognition(Stream stream, TimeFrame timeFrame)
{
try
{
Recognizer.Allocate();
Context.SetSpeechSource(stream, timeFrame);
}
catch (Exception exception)
{
this.LogError(exception);
}
}
public List <WordResult> Align(FileInfo audioUrl, List <string> sentenceTranscript)
{
var transcript = SentenceToWords(sentenceTranscript);
var aligner = new LongTextAligner(transcript, TupleSize);
var alignedWords = new Dictionary <int, WordResult>();
var ranges = new LinkedList <Range>();
//var texts = new ArrayDeque();
//var timeFrames = new ArrayDeque();
var texts = new LinkedList <List <string> >();
var timeFrames = new LinkedList <TimeFrame>();
ranges.AddLast(new Range(0, transcript.Count));
texts.Offer(transcript);
TimeFrame totalTimeFrame = TimeFrame.Infinite;
timeFrames.Offer(totalTimeFrame);
long lastFrame = TimeFrame.Infinite.End;
for (int i = 0; i < 4; i++)
{
if (i == 3)
{
_context.SetLocalProperty("decoder->searchManager", "alignerSearchManager");
}
while (texts.Count != 0)
{
Debug.Assert(texts.Count == ranges.Count);
Debug.Assert(texts.Count == timeFrames.Count);
var text = texts.Poll();
var frame = timeFrames.Poll();
var range = ranges.Poll();
if (i < 3 && texts.Count < MinLmAlignSize)
{
continue;
}
this.LogInfo("Aligning frame " + frame + " to text " + text + " range " + range);
if (i < 3)
{
_languageModel.SetText(text);
}
_recognizer.Allocate();
if (i == 3)
{
_grammar.SetWords(text);
}
_context.SetSpeechSource(audioUrl.OpenRead(), frame);
var hypothesis = new List <WordResult>();
Result speechResult;
while (null != (speechResult = _recognizer.Recognize()))
{
hypothesis.AddRange(speechResult.GetTimedBestResult(false));
}
if (i == 0)
{
if (hypothesis.Count > 0)
{
lastFrame = hypothesis[hypothesis.Count - 1].TimeFrame.End;
}
}
var words = new List <string>();
foreach (WordResult wr in hypothesis)
{
words.Add(wr.Word.Spelling);
}
int[] alignment = aligner.Align(words, range);
List <WordResult> results = hypothesis;
this.LogInfo("Decoding result is " + results);
// dumpAlignment(transcript, alignment, results);
DumpAlignmentStats(transcript, alignment, results);
for (int j = 0; j < alignment.Length; j++)
{
if (alignment[j] != -1)
{
alignedWords.Add(alignment[j], hypothesis[j]);
}
}
_recognizer.Deallocate();
}
ScheduleNextAlignment(transcript, alignedWords, ranges, texts, timeFrames, lastFrame);
}
return(new List <WordResult>(alignedWords.Values));
}
/// <summary>
/// Starts recognition process.
/// Recognition process is paused until the next call to startRecognition.
/// </summary>
/// <param name="clear">clear cached microphone data.</param>
public void StartRecognition(bool clear)
{
Recognizer.Allocate();
_microphone.StartRecording();
}