Student Name | School | Degree | Year | |
---|---|---|---|---|
Shaheer Mahmood | MCS | Undergraduate | Fourth | [email protected] |
Abdul Rauf | MCS | Undergraduate | Fourth | [email protected] |
Sanaullah | MCS | Undergraduate | Fourth | [email protected] |
Naqeebullah | MCS | Undergraduate | Fourth | [email protected] |
Inter School Idea ? | No |
Do you need expertises from another area: | No |
If Yes please provide details of expertises you need: |
Idea Name: | An Automated calls retrieval system |
Slogan: | a. A step to the safest world b. Guardians of the telephony |
Supervisor Name: | Dr Shibli Nisar |
Supervisor Designation: | Asst Prof |
Supervisor School: | MCS |
Supervisor Department: | EE |
Contact number: | 03005853845 |
Email ID: | [email protected] |
Abstract: | |
Many ill activities are done by terrorists using telephone and its very hard for LEAs to reach targeted person due to large dataset, its solution is to automate entire process based on AI. | |
What is the unmet need in society that your idea will fulfill ? | |
Nowadays LEAs manually retrieve calls of a specific user. It is impossible to do the same for millions of speakers. LEAs faced severe issues when retrieving call conversations manually from big databases.Our proposed system will automate the entire retrieving process and help direct the LEAs in ops. | |
Who needs it ? How many would benefit ? | |
This project will mainly benefit the Military or LEAs for security purposes. Moreover, this will not only assist the LEAs in their operation by retrieving the suspicious speakers calls from big database but also can be used in different commercial applications such as cellular operators etc. | |
How will the solution works | |
The project mainly consists of two phases. In phase 1, identification of specific calls will be identified using the speaker recognition model. Speaker recognition is widely used for the automatic authentication of speaker’s identity based on human biological features. Speaker recognition extracts, characterizes and recognizes the information about speaker identity. For feature extraction and speaker modeling many algorithms are being used. In our project MFCC ,VQ,GMM will be used. | |
Who are your competitors ? How is your solution different | |
To the best of our knowledge, no work has been done in Pakistan to automate the calls retrieval system in big database. The proposed solution is novel as no such kind of retrieval system is done based on speaker recognition approach. nusa188 | |
Status: | new |
Entry Date & Time: | 2021-12-10 (1221) |