Voice morphing


Published on

Published in: Technology
No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Voice morphing

  1. 1. PresentedPresented ByBy Sukhbeer KumarSukhbeer Kumar SupervisedSupervised ByBy Rajan sir & praveen SirRajan sir & praveen Sir Technical Seminar presentationTechnical Seminar presentation onon Voice morphingVoice morphing 1 SIT,MATHURA
  2. 2. SEMINAR OUTLINES •What It is? •Need of Voice Morphing •Description the Morphing. •Technical details of Morphing. •Application areas. SIT,MATHURA 2
  3. 3. Voice Morphing • Transition Phenomenon. • Technology developed at the Los Alamos National Laboratory in New Mexico, USA by George Papcun . SIT,MATHURA 3
  4. 4. What it actually performs ? • It is a technique to modify a source speaker's speech to sound as if it was spoken by a target speaker. • Voice morphing enables speech patterns to be cloned – And an accurate copy of a person's voice can be made that can wishes to say, anything in the voice of someone else. SIT MATHURA4
  5. 5. Need of voice morphing • Text To Speech (TTS) • In public speech systems • For special effects ( just like video or image morphing is done ). • To diminish Ethnical barriers. SIT,MATHURA5
  6. 6. Voice Morphing Process • Preprocessing or representation conversion. • Pitch and Envelope analysis. • Morphing which includes Warping and interpolation. • Signal re-estimation. SIT,MATHURA6
  7. 7. Block Diagram SIT,MATHURA7
  8. 8. Pre-Processing • Involves processes like signal acquisition in discrete form and windowing. SIT,MATHURA8
  9. 9. Pitch And Envelope Analysis • This process will extract the pitch. • Formant information in the speech signal. SIT,MATHURA9
  10. 10. Conversion SIT ,MATHURA10
  11. 11. Matching and Warping • DTW(Dynamic Time Warping) - Dynamic Time Warping (DTW) is used to find the best match between the pitch of the two sounds. SIT,MATHURA11
  12. 12. Signal Re-Estimation • Loss during Signal re-estimation - Due to signals being transformation into the cepstral domain, a magnitude function is used. This results in a loss of phase information in the representation of the data. SIT,MATHURA12
  13. 13. Summarized Block Diagram SIT,MATHURA13
  14. 14. Limitations   •Lots of normalizing problems. •Some applications require extensive sound libraries. •Different languages require different phonetics. •It is very seldom complete. SIT,MATHURA14
  15. 15. Advantages • Allows speech model to be duplicated and an exact copy of a person’s voice. • Powerful combat zone weapon. SIT,MATHURA15
  16. 16. Disadvantages • Use to pull out the useful information. • It hides the actual identity of the user. SIT,MATHURA16
  17. 17. Conclusion • The approach we have adopted separates the sounds into two forms: - Spectral envelope information - Pitch and voicing information. • Dynamic Time Warping - Aligns the sounds with respect to their pitches. • Signal re-estimation algorithm. - Frames are converted back into a time domain waveform. SIT,MATHURA17
  18. 18. Application Areas • Fake telephone conversations as evidence in courts of law. • Powerful battlefield weapon. - Provide fake orders to the enemy's troops, appearing to come from their own commanders. SIT,MATHURA18
  19. 19. Future Scope • Extending the functionality of tool. - Create a powerful and flexible morphing tool. • Increased user interaction. - Graphical User Interface could be designed and integrated to make the package more ‘user-friendly’. SIT,MATHURA19
  20. 20. Thank you!!! SIT,MATHURA20
  21. 21. Questions?? SIT,MATHURA21