Scribd
Upload
195 views16 pages

Voice Recognition

The document discusses voice recognition using machine learning. It describes how humans and computers recognize voice, the feasibility of the project, and the methodology which involves speech acquisition, analysis, and developing a user interface. Applications and flaws of voice recognition systems are also covered.

Uploaded by

Surya Karki
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
195 views16 pages

Voice Recognition

The document discusses voice recognition using machine learning. It describes how humans and computers recognize voice, the feasibility of the project, and the methodology which involves speech acquisition, analysis, and developing a user interface. Applications and flaws of voice recognition systems are also covered.

Uploaded by

Surya Karki
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Voice Recognition

(using Machine Learning)


Presented By:
Ayush Gupta
Surya Pratap Singh Karki
Vishal Verma
Lakshya Pande
INTRODUCTION
The project deals with understanding the concepts of
machine learning and its use in the real world scenario.
It involves implementing voice recognition via java
programming to convert speech to text via machine
learning and artificial intelligence. With this project we
intend to venture into the world of AI and help make
voice speech to text conversion an easier thing.
How Humans Recognize Voice?
When you speak, you create vibrations in the air.
These vibrations produces sound waves which the ear
conveys to the brain for processing.
How Computers might Recognize
Voice?
Acoustic Waveform ---> Acoustic Signal

Speech Recognition
Feasibility Study
On account of its flexible, software based nature, voice
recognition technology is incredibly versatile in terms of
potential applications. Identifying and authenticating a
user via the unique qualities of her/his voice is
contactless, quick, and easy to deploy in any scenario
where a microphone is available.

Also the project is quite economical, considering an


averagely efficient microphone would be sufficient
enough to record the voice of the user and thus provide
the data and input for conversion to suitable text and
results.
Tools required for proposed work :

Eclipse IDE

Operating System- Windows7 or further, Linux.

Java Development Kit 1.8

MS Office & Notepad (For documentation)

Microphone (Hardware)
Methodology
The process involves converting an acoustic signal,
captured by a microphone, to a set of words.
We will use the features of javax.speech.recognition
package that defines the Recognizer interface to support
speech recognition plus a set of supporting classes and
interfaces.
Voice Recognition System can be created by following
three steps:
- Speech Acquisition(Collection)
- Speech Analysis.
- User Interface Development.
Speech Acquisition (Collection):
For training purpose the speech is acquired using the microphone, for the
analysis.
The analog-to-digital converter (ADC)
translates this analog wave into digital data
that the computer can understand. To do
this, it samples, or digitizes, the sound by
taking precise measurements of the wave
at frequent intervals. The system filters the
digitized sound to remove unwanted noise,
and sometimes to separate it into different
bands of frequency.
The digital format of speech is used for
further analysis
Speech Analysis:

The First important step in Speech Analysis is to separate each word


from the ambient noise.
Further each spoken word is compared with the in built acoustic
model or dictionary which is created during the training session.
The above step is done with the help of an efficient speech detection
algorithm.
The SPHINX4 Speech recognition library will be used to detect and
recognize the words that one. The program will then determine what
the user was probably saying and either outputs it as text or issues a
computer command.
User Interface Development:

Final Step is to Develop a User Interface, so


that all users can use these system with
ease.
For Example: Speech Recognition System
of Windows 10 (called Cortana) looks so
simple.
APPLICATIONS
People with Disabilities:

A disable man using inbuilt Voice


Recognition System of its
Operating System to perform
his task.
Voice Recognition Systems can be embedded with
modern gadgets.
Example:
Television Amazon Echo Dot
Voice Recognition System: Flaws
and Weakness
Low signal-to-noise ratio.

Overlapping speech.

Differentiation b/w Homonyms.

Intensive use of computer power.


How to Remove Flaws and
Weakness of VRS?
Using High Quality Microphone.

Use Good Quality of Sound Cards.

System must be trained properly.

If possible work in quiet environment.


CONCLUSION

Human performance figures suggests that we still have


enormous room for improvement.

At present several new algorithms are developed to


implement voice recognition system.
THANK YOU

You might also like