Voice morphing

Views:
 
     
 

Presentation Description

No description available.

Comments

Presentation Transcript

VOICE MORPHING Presented By: STAFFI SINGLA 3609119 CSE-3RD YR GEETA INSTITUTE OF MANAGEMENT AND TECHNOLOGY KANIPLA,KURUKSHETRA:

VOICE MORPHING Presented By: STAFFI SINGLA 3609119 CSE-3 RD YR GEETA INSTITUTE OF MANAGEMENT AND TECHNOLOGY KANIPLA,KURUKSHETRA

List of contents:

List of contents ABSTRACT HISTORY INRODUCTION WHAT IT IS? NEED OF VOICE MORPHING PROCESS OF VOICE MORPHING TECHNICAL DETAILS APPLICATION AREAS ADVANTAGES DISADVANTAGES CONCLUSION FUTURE SCOPE BIBLIOGRAPHY

abstract:

abstract Voice morphing means the transition of one speech signal into another. Like image morphing, speech or voice morphing aims to preserve the shared characteristics of the starting and final signals, while generating a smooth transition between them. In Simpler terms it is being able to change the speech of one speaker to that of another speaker. Applications for Voice Morphing range from recreational ones to security ones.

history:

history Technology developed at the Los Alamos National Laboratory in New Mexico, USA by George Papcun .

INTRODUCTION:

INTRODUCTION It is a technique to modify a source speaker's speech utterance to sound as if it was spoken by a target speaker. Voice Morphing which is also referred to as voice transformation or voice conversion . Voice morphing transforms your natural voice into something bigger, smaller, bolder, or completely different. As you speak, the technology seamlessly modifies the pitch, speed, tone, and other key attributes of your voice. Depending on which morph you choose, the effect can be subtle or quite dramatic. Since the system is not a text-to-voice synthesizer but instead builds on your own voice, you can continue to speak naturally into your microphone while your new, morphed voice is heard inworld .

What it actually performs ? :

What it actually performs ? Voice morphing technology enables a user to transform one person’s speech pattern into a different pattern with distinct characteristics while preserving the original meaning. The new characteristics are, in most applications, those of another speaker. Voice morphing enables speech patterns to be cloned -- And an accurate copy of a person voice can be made that can wishes to say, anything in the voice of someone else.

CONTD….:

CONTD….

Need of voice morphing :

Need of voice morphing Text To Speech (TTS) . In public speech systems. For special effects ( just like video or image morphing is done. )

Voice Morphing Process :

Voice Morphing Process Pre-processing or representation conversion. Pitch and Envelope analysis. Morphing which includes Warping and interpolation. Signal re-estimation.

Pre-Processing:

Pre-Processing Involves processes like signal acquisition in discrete form and windowing.

Pitch and Envelope analysis. :

Pitch and Envelope analysis. This process will extract the pitch. Formant information in the speech signal

Block Diagram:

Block Diagram

Matching and Warping:

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.

Signal Re-Estimation :

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 .

Summarized Block Diagram:

Summarized Block Diagram

Application Areas :

Application Areas Fake telephone conversations as evidence in courts of law. Video and image morphing is extensively used for film and graphical special effects In text to speech system converts normal language text into speech; other systems render symbolic linguistic representations like phonetic transcription into speech. Powerful battlefield weapon. Provide fake orders to the enemy's troops, appearing to come from their own commanders. In public speech systems we can make the sound to be of a popular public speaker. We can implement that in many places like railway announcements .

Advantages :

Advantages Allows speech model to be duplicated and an exact copy of a person’s voice. Powerful combat zone weapon.

Disadvantages:

Disadvantages Voice detection is done via sophisticated 3d rendering but there are a lot of normalizing problems. It hides the actual identity of the user. Some applications require extensive sound libraries. The different langauge requires different phonetics and thus updating or extending is tedious. It is very seldom complete (we may not be able add every small talk, every phonetics into the database. Lots of normalizing problems.

Conclusion :

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.

Future Scope :

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-interactive’.

bibliography:

bibliography

PowerPoint Presentation:

THANKS A LOT! Any Queries??

authorStream Live Help