Speaker recognition based on semantic indexing

Abstract EN

In this paper, a new pitch extraction method is established to be employed in improving the performance of the Eigen voices problem.

This required indexing the pitch of the voice in a document matrix and then mapping the voice documents into preserved semantic features.

The proposed voice recognition system was built to be operated in two phases; enrollment and recognition.

Closed dataset of different voices belong to different sexes and ages of speakers were enrolled in the first phase.

The results of the recognition phase were promising of about 81 % for both sexes.

This ensures the successful recognition task and the efficiency of the proposed system.