Scribd
Upload
28 views11 pages

Voice

This document discusses voice recognition (also called speech recognition), which is an application of artificial intelligence that converts spoken words to machine-readable text. It provides examples of speech recognition applications in cell phones and outlines two common statistical models used - Hidden Markov Models and Dynamic Time Warping. The document also notes some challenges with speech recognition including sound-alike errors and issues recognizing mumbled speech. In conclusion, it emphasizes that the environment and other factors like noise levels can impact the performance of speech recognition systems.

Uploaded by

Sakshi Agarwal
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
28 views11 pages

Voice

This document discusses voice recognition (also called speech recognition), which is an application of artificial intelligence that converts spoken words to machine-readable text. It provides examples of speech recognition applications in cell phones and outlines two common statistical models used - Hidden Markov Models and Dynamic Time Warping. The document also notes some challenges with speech recognition including sound-alike errors and issues recognizing mumbled speech. In conclusion, it emphasizes that the environment and other factors like noise levels can impact the performance of speech recognition systems.

Uploaded by

Sakshi Agarwal
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/ 11

Rajshree Institute Of

Management And Technology

Topic-Voice Recognition
Presented by-: Sakshi Agarwal
Pragati Dixit
Priyanka
(CS 4th Year)
Artificial Intelligence (AI):-
Definition:- The study and design of intelligent
agents & also used to describe a property of
machine or programs.

Among researchers hope machines will exhibit


are reasoning, knowledge, planning, learning,
communication, perception and the ability to
move and manipulate.
Application of AI :-
Pattern Recognition
Hand Writing Recognition
Speech Recognition
Natural Language Processing
Face Recognition
Artificial Recognition
Artificial Creativity
Non linear controls and Robots
Speech Recognition :-
Speech recognition converts spoken words to machine-
readable input.
It is also called Voice Recognition.

Speech recognition includes-


Voice dialling
Content-based spoken audio search
Speech-to-text processing

• Audio visual Speech Recognition is also present in which it


takes lip reading also apart from speech recognition.
Speech Recognition in Cell phones :-
Callers words are captured and digitized by
speech-recognition system.
Digitized voice is split into frequency
components, called spectral representations.
The components are translate into phonemes.
Complex models and algorithms determine a
likely translation.
Performance of speech recognition
system :-
 It is usually specified in terms of accuracy and speed.
Accuracy may be measured in terms of performance
accuracy which is usually rated with word error rate,
whereas speed is measured with the real time factor.
 Dictation machines can achieve very high performance
in controlled condition and require only a short period of
training.
 Optimal condition usually assume that users-
 Have speech characteristics which match the training
data.
 Can achieve proper speaker adaption.
 Work in clean and no noise environment.
There are two models on statistically based Speech Recognition :-

HiddenMarkov Model (HMM model)


Dynamic Time Wrapping (DTW model)
Applications of Speech Recognition:
Healthcares
 In this event in the wake of Speech recognition
technologies MT haven’t absolute.
• Military-
• High-performance fighter aircraft-
 Speech recognizers have been operated successfully.
 Some important conclusion from the work are as follows:
 Speech recognition has definite potential for reducing
pilot workload, but this potential was not realized
consistently.
 Achievement of very high recognition accuracy(95% or
more) was the most critical factor for making the speech
recognition system useful with lower recognition rates ,
pilots would not use the system.
Failure of Speech Recognition:-

The computer has trouble with “sound-alike” errors.


It’s hard to get mad at the computer for not recognizing
mumbling. But it can be frustrating when you think you
are speaking clearly, and it is just isn’t good enough.
For example when I said: I sure look forward to seeing
you
The computer heard: Assure Look forward to seen in
you
When I repeated the same words with better
enunciation, the computer got it right.
Conclusion :-

• This paper presents the Speech Recognition in


Artificial Intelligence systems and it is important
to consider the environment in which the speech
recognition system has to work.

• The grammar used by the speaker and accepted by


the system, noise level, noise type, position of the
microphone , and speed and manner of the user’s
speech are some factors that may affect the quality
of speech recognition.
THANK YOU

You might also like