International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 02 | Feb -2017
p-ISSN: 2395-0072
www.irjet.net
Voice Recognition Eye Test Madhavi Priya 1Student,
Dept. of Electronics & Communication Engineering, Dronacharya group of institution, India
---------------------------------------------------------------------***--------------------------------------------------------------------1.1 High Level Design Abstract - In this paper, an attempt has been made to review on design of voice recognition eye test that is capable of performing the entire eye test on its own. This project attempted to design and implement a voice recognition system that would identify different users based on previously stored voice samples. Each user inputs audio samples with a keyword of his or her choice. This input was gathered but successful processing to extract meaningful spectral coefficients was not achieved. These coefficients were to be stored in a database for later comparison with future audio inputs. Afterwards, the system had to capture an input from any user and match its spectral coefficients to all previously stored coefficients on the database, in order to identify the unknown speaker.
Rationale The idea is that we want to bring the common Snellen eye test to the household. The test is very simple in that it requires the user to stand a distance away from a chart and read letters to estimate one's visual acuity. So we thought, why not bring the test from the eye doctor's office to the household? In this way, people can take the initiative in taking care of their health in a way that does not require having to drive over and wait until it is their turn to complete the test which, in the end, takes a fraction of the time spent driving and waiting. Also, this can reduce the time it takes to receive a proper diagnosis for one's eyesight when one visits the doctor after having taking the household exam. Also, our eye test could be used in the doctor's office to streamline the process of determining a person's visual acuity since so many of these tests are performed each day
Key Words: Recognition, Eye, Design, Database, Processing
1. INTRODUCTION It starts by displaying large letters and waits on the user to guess which letter has been displayed. The user speaks his/her guess into the microphone. The speech recognition portion uses energy threshold to make sure background noise does not interfere with the user's guess. The system will then determine the next step based on whether the user guessed the displayed letter correctly or not. If the user guesses enough correctly, the text size will continue getting smaller until the user either reaches the minimum text size (corresponding to 20/20) or starts guessing enough incorrectly. If the user guesses too many letters incorrectly, the system will display the result corresponding to the current text size (e.g. 20/30). The thresholds for amount guessed and amount guessed correctly are set in the code. Our eye test uses a dictionary containing the letters "A", "E", "I", "R", and "L" with the same 6 possible text sizes for each of these letters.
1.2 BPF Design The range of spoken frequencies is 300 Hz to 3400 Hz. This means we only need to worry about frequencies in that range, so we can filter out the rest. We set up our band-pass filter and determined the resistance and capacitance values according to the cutoff frequency equation below. This equation applies to both the cutoff frequency for the low-pass filter and the highpass filter.
Equation for Cutoff Frequency Calculation
Š 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 1671