Abstract
This paper presents a technique for isolated word recognition from speech signal using Spectrum Analysis and Linear Predictive Coding (LPC). In the present study, only those words have been analyzed which are commonly used during a telephonic conversations by criminals. Since each word is characterized by unique frequency spectrum signature, thus, spectrum analysis of a speech signal has been done using certain statistical parameters. These parameters help in recognizing a particular word from a speech signal, as there is a unique value of a feature for each word, which helps in distinguishing one word from the other. Second method used is based on LPC coefficients. Analysis of features extracted using LPC coefficients help in identification of a specific word from the input speech signal. Finally, a combination of best features from these two methods has been used and a hybrid technique is proposed. An accuracy of 94% has been achieved for sample size of 400 speech words.
Highlights
In today’s era of information technology, mobile communication is the fastest growing field and most popular medium of communication
This paper presents a technique for isolated word recognition from speech signal using Spectrum Analysis and Linear Predictive Coding (LPC)
These parameters help in recognizing a particular word from a speech signal, as there is a unique value of a feature for each word, which helps in distinguishing one word from the other
Summary
In today’s era of information technology, mobile communication is the fastest growing field and most popular medium of communication. The same media is being misused for enemies of the society like terrorists and rioters These anti-social people use some typical words or phrases during their communication on mobile phones. If these interactions can intercept timely, lot of lives can be saved from those anti social elements. A hybrid technique is proposed, which is able to recognize pre-determined isolated words from speech signals. Speech signals of different 400 words have been collected from each young volunteer (age 19-21 years). Ning used inverse of spectral features called cepstral for word recognition [5]. A method is proposed by considering most discriminating features from Spectrum analysis and LPC analysis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
