The Algorithms of Speech Recognition,Programming and Simulating in Matlab


Authors : Mantu Bera.

Volume/Issue : Volume 3 - 2018, Issue 3 - March

Google Scholar : https://goo.gl/DF9R4u

Scribd : https://goo.gl/pkUtqH

Thomson Reuters ResearcherID : https://goo.gl/3bkzwv

Abstract : My aim of this thesis work is to Test the algorithms of speech recognition. I have programmed and simulated the designed systems for speech recognition’s Algorithms in MATLAB.Hence,There are two systems have been designed within this thesis.First One is based on the shape information of the cross-correlation plotting. The Second one is to use the Wiener Filter for realizing the speech recognition. The simulations of the systems which have been Programmed in MATLAB are accomplished by using the microphone for recording of the speaking words. After running the program in MATLAB, The system will ask people to record the words for three times.First and second recorded words are different words which will be used as the reference signals in the designed systems. The third recorded word is the same word as the one of the first two recorded words. After recording completed, the words will become the signals’ information that will be sampled and stored in MATLAB. Then MATLAB will be able to give the judgment that which word has been recorded at the third time comparing with the first two reference words according to the algorithms programmed in MATLAB. I invite different people from different Places with different utterence to test the designed systems. The results of simulations for both designed systems prove that both of the designed systems work well whenever the first two reference recordings and the third time recording are recorded from the same person. But the designed systems have the defects when the first two reference recordings and the third recording are recorded from the different people. However, if the testing environment is quiet enough and the speaker is the same person for recordings of three times, the successful probability of the speech recognition approach to 100 percent. Thus, the designed systems really work well for the speech recognition.

Keywords : Algorithm of Speech recognition, MATLAB programming, Recordings, Cross-correlation and auto correlation,FIR Wiener Filter, Simulations.

My aim of this thesis work is to Test the algorithms of speech recognition. I have programmed and simulated the designed systems for speech recognition’s Algorithms in MATLAB.Hence,There are two systems have been designed within this thesis.First One is based on the shape information of the cross-correlation plotting. The Second one is to use the Wiener Filter for realizing the speech recognition. The simulations of the systems which have been Programmed in MATLAB are accomplished by using the microphone for recording of the speaking words. After running the program in MATLAB, The system will ask people to record the words for three times.First and second recorded words are different words which will be used as the reference signals in the designed systems. The third recorded word is the same word as the one of the first two recorded words. After recording completed, the words will become the signals’ information that will be sampled and stored in MATLAB. Then MATLAB will be able to give the judgment that which word has been recorded at the third time comparing with the first two reference words according to the algorithms programmed in MATLAB. I invite different people from different Places with different utterence to test the designed systems. The results of simulations for both designed systems prove that both of the designed systems work well whenever the first two reference recordings and the third time recording are recorded from the same person. But the designed systems have the defects when the first two reference recordings and the third recording are recorded from the different people. However, if the testing environment is quiet enough and the speaker is the same person for recordings of three times, the successful probability of the speech recognition approach to 100 percent. Thus, the designed systems really work well for the speech recognition.

Keywords : Algorithm of Speech recognition, MATLAB programming, Recordings, Cross-correlation and auto correlation,FIR Wiener Filter, Simulations.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe