PresentedPresentedByBy

H.Mohammed.SabirH.Mohammed.Sabir09AT1A046109AT1A0461

Supervised Supervised ByBy

Shreedhar Sir Shreedhar Sir

Voice morphingVoice morphing

SEMINAR OUTLINES

What It is?

Need of Voice MorphingDescription the Morphing.Technical details of Morphing.Application areas.

What is Voice Morphing ??

Voice morphing is a technique for modifying a (source) speaker's speech to sound as if it were spoken by a different (target) speaker.

In Simpler terms it is being able to change the speech of one speaker to that of another speaker.

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

Applications for Voice Morphing range from recreational ones to security ones.

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.

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.

How to Morph Voice ??

We need to effectively change the pitch from that of a male speaker to that of a female speaker. If we reminisce the excitation signal has information about the speaker.

We find the LPC coefficients for the Source and Target Signals and using these coefficients we are going to interpolate between the two Signals.

We get the New LPC (linear predictive coding) coefficients using the formula

new lpc coeff = [const*(lpc source) + (1-const)

(lpc target)]

0 <= const <= 1 …

How to Morph Speech ?? (contd…)

The pitch of a female speaker will be close to twice that of the male speaker. In our example the pitch of the male speaker is 141Hz and that of the female speaker is 210Hz.

So we need to develop some time stretching algorithm so that we can implement pitch shifting. We obtain the residue of the source signal and stretch it according to the value of the const. The const indicates what is the position of morphed signal in between the source and target.

For example if const = 0.2 then the morphed signal will be closer in pitch to the source signal and a value of 0.8 for const will result in a pitch that is closer to the target signal.

How do we shift the Pitch ??

We break the residue signal into small windows and introduce fade in and fade out for each block. We recombine everything to form the pitch shifted signal. Based on the alpha we can time stretch the residue according to our requirements.

How do we Morph finally ??

• We now have the pitch shifted residue signal and the new LPC coefficients. We should resample the pitch shifted signal so that it is played at a faster rate. [Remember when we pitch shift then the residue will last longer]. If we inverse filter the resampled pitch shifted residue then we can effect morphing.

Block Diagram

Time Domain Plots of Source and Target featuring the Pitch

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

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.

Limitations 

Lots of normalizing problems.

Some applications require extensive sound libraries.

Different languages require different phonetics.

It is very seldom complete.

Advantages

Allows speech model to be duplicated and an exact copy of a person’s voice.

Powerful combat zone weapon.

Disadvantages

Use to pull out the useful information.

It hides the actual identity of the user.

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.

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.

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’.

BIBLIOGRAPHY:

• Ye, H. and S. Young (2003). "Perceptually Weighted Linear Transformations for Voice Conversion". Eurospeech 2003, Geneva. 

• Ye, H. and S. Young (2004). "High Quality Voice Morphing". Int Conference Acoustics Speech and Signal Processing, Montreal, Canada. 

• High quality Voice Morphing Hui Yeand Steve Young. • Quality-enhanced Voice Morphing

Thank you!!!

Questions??