Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : Linear Discriminant Analysis (LDA)


Encryption VoIP based on Generated Biometric Key for RC4 Algorithm

Raya W. Abd Aljabar; Nidaa F. Hassan

Engineering and Technology Journal, 2021, Volume 39, Issue 1B, Pages 209-221
DOI: 10.30684/etj.v39i1B.1755

Voice over Internet Protocol (VoIP) calls are susceptible to interfere at many points by many attackers, thus encryption considered an important part in keeping VoIP.
In this paper, Encryption VoIP based on Generated Biometric Key for RC4 Algorithm is proposed to encrypt the voice data before transmitting it over the network. The system uses a stream algorithm based on RC4 encryption with the new method of biometrics based Key generation technique. This system has generated complex keys in offline phase which is formed depend on features extracted using Linear Discernment Analysis (LDA) from face images.
The experimental work shows that the proposed system offers secrecy to speech data with voice cipher is unintelligible and the recovered voice has perfect quality with MSR equal to zero and PSNR equal to infinity.

Age Estimation in Short Speech Utterances Based on Bidirectional Gated-Recurrent Neural Networks

Ameer A. Badr; Alia K. Abdul-Hassan

Engineering and Technology Journal, 2021, Volume 39, Issue 1B, Pages 129-140
DOI: 10.30684/etj.v39i1B.1905

Recently, age estimates from speech have received growing interest as they are important for many applications like custom call routing, targeted marketing, or user-profiling. In this work, an automatic system to estimate age in short speech utterances without depending on the text is proposed. From each utterance frame, four groups of features are extracted and then 10 statistical functionals are measured for each extracted dimension of the features, to be followed by dimensionality reduction using Linear Discriminant Analysis (LDA). Finally, bidirectional Gated-Recurrent Neural Networks (G- RNNs) are used to predict speaker age. Experiments are conducted on the VoxCeleb1 dataset to show the performance of the proposed system, which is the first attempt to do so for such a system. In gender-dependent system, the Mean Absolute Error (MAE) of the proposed system is 9.25 years, and 10.33 years, the Root Mean Square Error (RMSE) is 13.17 and 13.26, respectively, for female and male speakers. In gender_ independent system, the MAE of the proposed system is 10.96 years, and the RMSE is 15.47. The results show that the proposed system has a good performance on short-duration utterances, taking into consideration the high noise ratio in the VoxCeleb1 dataset.