It is possible to extract the default phonemes for a given word via SAPI by:
- Voice word with text-to-speech and store output in a .wav
- Use the .wav as input for speech recognition
- Upon recognition of the word extract the phonemes from the recognized phrase elements
However I have not been able to capture (if available) emphasis markers ("1" and "2" per the American English Phoneme Table). Is there a way to do this?
EDIT: Here is what I've attempted so far (not pretty, but functional). Sadly it looks like the SpeechVisemeFeature always shows "SVF_None," even when I manually add emphasis to a word via SAPI Speech Dictionary modification. Does anyone know why this is?
using System;
using System.Threading;
using SpeechLib;
using System.Windows.Forms;
namespace PhoneEmphasis
{
class Program
{
static string myWord = "hello";
static SpPhoneConverter c = new SpPhoneConverter();
static Thread t = null;
static void Main(string[] args)
{
c.LanguageId = 1033;
t = new Thread(test);
t.Start();
t.Join();
Console.WriteLine("done");
Console.ReadLine();
}
private static void test()
{
SpVoice v = new SpVoice();
//v.EventInterests = SpeechVoiceEvents.;
v.Phoneme += new _ISpeechVoiceEvents_PhonemeEventHandler(Phoneme_Handler);
v.EndStream += new _ISpeechVoiceEvents_EndStreamEventHandler(EndStream_Handler);
v.Speak(myWord, SpeechVoiceSpeakFlags.SVSFlagsAsync);
Application.Run();
}
private static void Phoneme_Handler(int StreamNumber, object StreamPosition, int Duration, short NextPhoneId, SpeechVisemeFeature Feature, short CurrentPhoneId)
{
Console.WriteLine("Phoneme = " + c.IdToPhone(CurrentPhoneId).ToString() + " , VisemeFeature = " + Feature.ToString());
}
private static void EndStream_Handler(int StreamNumber, object StreamPosition)
{
Console.WriteLine("end stream!");
t.Abort();
}
}
}