Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Text to-speech & voice recognition

This is a translated version of the Slides submitted online by Vangos Sun, Mar 21 2010 16:25. I do not own this material, simply translated it.

  • Be the first to comment

Text to-speech & voice recognition

  1. 1. Athens University of Economics
  2. 2. Communicating with PC Traditional ways Mouse Keyboard (printer)
  3. 3. Communicating with PC Traditional Ways Keyboard Mouse Printer Modern Ways touch speech Movement
  4. 4. Speech Speech Synthesis
  5. 5. Speech Speech Synthesis Speech Recognition
  6. 6. Speech Synthesis Input: Text Output: Audio stream
  7. 7. Speech Recognition Input: Audio stream Output: Text
  8. 8. Used In Movies 
  9. 9. Used In Movies  Automatic translations
  10. 10. Used In Movies  Automatic Translation Learning Foreign Languages
  11. 11. Used In Movies  Automatic Translation Learning Foreign Languages Mobiles
  12. 12. Used In Movies  Automatic Translation Learning Foreign Languages Movies Robotics
  13. 13. Used In Movies  Automatic Translation Learning Foreign Languages Movies Robotics Games Nintendo Wii Project Natal (Kinect)
  14. 14. What options do we have today; Acapela
  15. 15. What options do we have today; Acapela Java Speech API
  16. 16. What options do we have today; Acapela Java Speech API Dictaphones
  17. 17. Τι επιλογές έτοσμε σήμερα; Acapela Java Speech API Dictaphones etc Still a long way to go….
  18. 18. What we see here Windows Speech API (SAPI)with .NET 4.0! System.Speech;
  19. 19. Why SAPI; free Quite accurate Easily programmable
  20. 20. History of SAPI 1994: SAPI 1.0 Windows 95 / Windows NT
  21. 21. History of SAPI 1994: SAPI 1.0 Windows 95 / Windows NT 1998: SAPI 4.0 C++ wrapper classes ActiveX for Visual basic
  22. 22. History of SAPI 1994: SAPI 1.0 Windows 95 / Windows NT 1998: SAPI 4.0 C++ wrapper classes ActiveX for Visual basic 2006: SAPI 5.3 Windows Vista
  23. 23. Ιστορία τοσ SAPI 1994: SAPI 1.0 Windows 95 / Windows NT 1998: SAPI 4.0 C++ wrapper classes ActiveX for Visual basic 2006: SAPI 5.3 Windows Vista 2009: SAPI 5.4 Windows 7
  24. 24. Αλλαγές στα Windows Vista & 7 Αναβαθμισμένη Speech Recognitionengine
  25. 25. Changes in Windows Vista & 7 Upgraded Speech Recognition engine Separate application with its own GUI
  26. 26. Changes in Windows Vista & 7 Upgraded Speech Recognition engine Separate application with its own GUI Checks the UI operation
  27. 27. Changes in Windows Vista & 7 Upgraded Speech Recognition engine Separate application with its own GUI Checks the UI operation Supports more languages - English US & UK, Chinese traditional & simplified,Japanese, German, French, Spanish
  28. 28. Changes in Windows Vista & 7 Upgraded Speech Recognition engine Separate application with its own GUI Checks the UI operation Supports more languages - English US & UK, Chinese traditional & simplified,Japanese, German, French, Spanish Managed code speech API (.ΝΕΤ 3.0)
  29. 29. What we useTechnologies• .NET Framework 4.0• C# programming language• Windows Presentation FoundationTools• Windows 7• Visual Studio 2010• FREE @ MSDNAA
  30. 30. Windows Speech Synthesis Converts words into voice Internet settings like: intensity Pronunciation (voice) Introducing WAV files By default, uses Microsoft Anna
  31. 31. DEMO 1
  32. 32. Windows Speech Recognition Uses machine learning algorithms Continuously Trained Trains using the user’s voice Can be used for remote control of thePC 
  33. 33. DEMO 2
  34. 34. Links Venus StudentGuru Exploring Speech Recognition &Synthesis Speech Recognition with C# - Dictationand custom grammar
  35. 35. Thank you Vangos Pterneaswww.vangos.euwww.vangos.eu/blog

×