VOICE MORPHING

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
BY
TEJASWI MAMIDIPALLY-20VE1A0536

UNDER THE GUIDANCE OF

MR K.KRISHNA REDDY
ASSISTANT PROFESSOR
(2020-2024)
INTRODUCTION

 Technology developed at the Los Alamos National

Laboratory in New Mexico, USA by George Papcun.
 It is a Transition Phenomenon.
 It is a technique to modify a source speakers 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 persons voice can be made that can
wishes to say, anything in the voice of someone else.
HARDWARE AND SOFTWARE REQUIREMENTS

Hardware Requirements:
 Computer
 Microphone
 HARDWARE AND SOFTWARE REQUIREMENTS

Software Requirements:
 Python
 Python Libraries
 Jupyter Notebook or IDE
ADVANTAGES

 Allows speech model to be duplicated and an exact copy

of a person’s voice.
 It is used technology to change the voice of one
person to sound like voice of another.
 A good system can shift the pitch to make a male voice
sound like a female while maintaining the same timing
and pronunciation.
 It is used for a variety of purposes like producing
cartoons where one person does the voices of a number of
characters.
IMPLEMENTATION

The algorithm to be used is shown is the simplified block diagram

given below. The algorithm contains a number of fundamental
signal processing methods including sampling, the discrete
Fourier transform and its merse, cepatral analysis. However the
main process can be categorized as follows
 Pre-processing or representation conversion: This involves
processes like signal acquisition in discrete form and windowing
 Cepstral analysis or Pitch and Envelope analysis: This process
will extract the pitch and formant information in the speech
signal
 Morphing which includes Warping and interpolation.
 Signal re-estimation
TECHNOLOGIES

Digital Signal Processing (DSP) Libraries

Waveform Generation
Pitch and Time Manipulation
Voice Conversion
Speech Synthesis Libraries
 Deep Learning Frameworks
CONCLUSION

 The approach separates the sounds into two forms:

- spectral envelope information and
- pitch information.
These can then be independently modified. The morph is
generated by splitting each sound into two forms:
- a pitch representation and
- an envelope representation.
At each corresponding frame, the pitch and envelope information
are separately morphed to produce a final morphed frame.
These frames are then converted back into a time domain
waveform using the signal re-estimation algorithm
REFERENCES

High quality voice morphing Hui. Yeand Steve Young.

Quality-enhanced voice morphing voice Morphing
http://www.ime.usp.hr-m/SMC10 Voice.pdf
http://mi.cog.cam.ac.uk/-hy216/VoiceMorphingPr| html
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’.
QUERIES???????????
THANKYOU !!!!