Bonfring International Journal of Research in Communication Engineering, Vol. 6, Special Issue, November 2016 48
Abstract--- Artificial intelligence involves studying the
thought processes of human beings and also representing
those processes via computers and robots like man made
machines. Speech recognition system lets user do other works
simultaneously so that the user can concentrate on
observation and manual operations. With the help of speaker
recognition technology we can help physically challenged
skilled persons. So that they can do their works without the
help of others. This Artificial Speech Recognition technology
is also used in various applications. Now days this technology
is also used by CID officers in order to trap the criminal
activities.This technology is also used in military applications.
Keywords--- NLP, LPC, DFT, MMSE Technique.
I. INTRODUCTION
RTIFICIAL intelligence involves two basically deals
with studying the thought processes of human beings and
then representing those processes via computer[1].
There is one artificial intelligence method through which we
can communicate with a computer in a natural language like
English which is termed as Natural Language
Processing(NLP). The main objective of a NLP program is to
understand the applied input and then initiate related action.
II. DEFINITION
Artificial Intelligence is the science and engineering of
making intelligent machines, especially intelligent computer
programs so that it can serve most of user needs[2].AI implies
Artificial Intelligence. Intelligence is the factor which cannot
be defined but whereas AI can be defined as branch of
computer science which deals with the simulation of machine
that exhibits intelligent behavior as the human being. Speech
recognition is considered to be one of the applications of the
artificial intelligence which mainly deals with the translation
of user spoken words into the corresponding text.
III. OBJECTIVES
1) Deals with understanding human thinking capabilities:
This means to obtain deep knowledge of human
memory, Problem solving ability, learning and
decision making etc.
S.V. Viraktamath.
Chaitra Prakash Shet, Student, Department of Electronics &
Communication, Shri Dharmasthala Manjunatheshwara College of
Engineering and Technology, India. E-mail:chaitraprakashshet@gmail.com
Pooja Ravindra Nayak, Student, Department of Electronics &
Communication, Shri Dharmasthala Manjunatheshwara College of
Engineering and Technology, India. E-mail:poojaravindranayak@gmail.com
DOI:10.9756/BIJRCE.8199
2) Replaces human in intelligent tasks: Results in
building of system in order to help humans think
better, faster and deeper.
3) Enhance human intelligence: It implies building
program to exceed human intelligence.
4) Deals with Coherent discourse: Communication with
people using natural language involves intelligent
dialogue.
IV. SPEAKER INDEPENDENCY
Usually the speech quality varies from one person to
another person. So it becomes difficult to design an electronic
machine that recognizes everyone’s voice. The system is made
simpler and also more reliable by designing it in order to
recognize single person’s voice. The computer is trained to the
voice of the particular individual. Such developed system is
called speaker-dependent system. Speaker independent
systems can be used by anybody, as it recognizes any voice,
although the characteristics vary widely from one speaker to
another. These speaker independent systems are costly and
complex to construct. These systems have got limited
vocabularies. There are some factors that may affect the
quality of speech recognition. That includes 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 and so on.
V. ENVIRONMENTAL IMPACT
The recognition rate usually drops widely when a system is
trained and tested under different conditions. It is necessary
that we should be aware of the variations present when
different microphones are used in training, testing, and also
during development of required procedures. Such that with
this the accuracy of recognition systems can be improved to
greater extent.
Accuracy of recognition systems are going to be degraded
mainly because of Acoustical distortions. Obstacles for
robustness include additive noise from machinery, competing
talkers, reverberation from surface reflections in a room, and
spectral shaping by microphones and also the vocal tracts of
individual speakers and so on. The sources of distortions are
categorized as additive noise and distortions resulting from the
convolution of the speech signal with an unknown linear
system. There are various algorithms proposed for speech
enhancement. They are given as follows:
1. Spectral subtraction of the obtained DFT coefficients.
2. The DFT coefficients of corrupted speech are
estimated by applying MMSE technique Convoluted
S.V. Viraktamath, Chaitra P. Shet and Pooja R. Nayak
Artificial Intelligence and its Application in Speech
Recognition
A
ISSN 2277 - 5080 | © 2016 Bonfring