Abstract:
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. Speaker identification technologies are widely applied in voice authentication, security and surveillance,electronic voice eavesdropping, and identity verification.The proposed model will automate the entire process by recognizing the suspicious speaker and dig out all the audio conversations of target.To address problem, AI based solution is recommended .This project will mainly benefit the Military or LEAs for security purposes. Moreover. The proposed model can easily be implemented in any international or national military organization or for commercial purposes, which will help in assisting international collaborations.
