| Idea Name: |
AHIT |
| Slogan: |
Hear better, Live Better |
| Supervisor Name: |
Dr. Shibli Nisar |
| Supervisor Designation: |
Assistant Professor |
| Supervisor School: |
MCS |
| Supervisor Department: |
Electrical Engineering |
| Contact number: |
0300585384 |
| Email ID: |
[email protected] |
| Abstract: |
| Auto identification of hearing impairment based on audiogram & speech recognition threshold using automatic speech recognition. Secondly, the aim of this research project is to identify digitally recorded, edited & evaluated bi & mono syllabic Pashto words with the goal to identify homogeneous words that could be used to measure the SRT in native Pashto speaker of KPK, Baluchistan & Afghanistan. |
| What is the unmet need in society that your idea will fulfill ? |
| a. Early diagnosis of hearing loss by audiologist
b. Lack of expert audiologists in Pakistan
c. Long time appointment, consultancy fee, unavailability of equipment & qualified practitioners in remote areas
d. SRT test is carried out in English language causing a communication barrier in remote areas |
| Who needs it ? How many would benefit ? |
| According to WHO approx 360 to 538 million people worldwide are suffering from hearing loss. AHIT will automate the entire hearing testing and will help the audiologists to have the second option in form of SRT. This can be easily implemented in all national and international hospitals. |
| How will the solution works |
| AHIT will automate the entire hearing loss test . In audiometry, the patient will respond with yes/no on tones of various freq. The result will be displayed based on the frequency being heard. In speech recognition, the patient repeat spondee words (Pushto) uttered by the machine. Response will be captured through the speech signal & the sys will identify the right & wrong guesses to calculate SRT of a subject. Two main features of speech recognition wil be feature extraction & classification. |
| Who are your competitors ? How is your solution different |
| To the best of our knowledge, no or very little work has been done in automation of hearing loss testing in general and SRT for Pashto native speakers in particular. This will be the first attempt to automate the entire hearing loss testing based on speech recognition for both audiogram and SRT. |
| Status: |
new |
| Entry Date & Time: |
2021-12-19 (0020) |
