مقارنة بعض نماذج الضوضاء الصوتية وتأثيرها على التشخيص الصوتي لبصمات برامج التواصل الاجتماعي

Sarah Taha Ali; Wleed Abdalaa Araheemah; Mohammed Ahmed Taiye

doi:10.51173/jt.v5i2.1058

Authors

Sarah Taha Ali Technical College of management - Baghdad, Middle Technical University, Baghdad, Iraq
Wleed Abdalaa Araheemah Technical College of management - Baghdad, Middle Technical University, Baghdad, Iraq
Mohammed Ahmed Taiye Linnaeus University, Sweden

DOI:

https://doi.org/10.51173/jt.v5i2.1058

Keywords:

Voiceprint, Noise Models, Audio Filters, Wavelet Transform, Median Filters, Band Pass Filter

Abstract

The importance of preserving voiceprints as well as verifying their authenticity has increased, especially since reliance on them in the Corona period made many users rely on them in their work in directing administrative orders. As a result, this research came in an attempt to employ several algorithms for neural networks to verify voiceprints for (50-100 (1 person and for each person) (10-20) samples were taken. The results showed that the wavelet transform was affected by (the number of people, the number of sound signatures, and the noise). It was taken from one of the most famous social networking programs, which is (whatsApp), and the results showed that the design for each the type of noise and the type of filter adopted to reduce the effect of noise, reached the highest rating (99.2%) and it is due to the convergent neural network CNN (Band pass filter), while the worst rating reached 95.5% and it is due to the case of the convergent network CNN (AWGN) as shown Results The ability of some filters to increase the classification accuracy of the convention neural network and reduce the effect of noise.

Downloads

Download data is not yet available.

Author Biography

Mohammed Ahmed Taiye, Linnaeus University, Sweden

References

Das, Soubhik "A Machine Learning Model for Detecting Respiratory Problems using Voice Recognition " 2019 IEEE 5th International Conference for Convergence in Technology (I2CT) IEEE, 2019.

Song, Zhaojuan "English speech recognition based on deep learning with multiple features " Computing 102 3 (2020): 663-682.

Ali, Ashraf Tahseen, Hasanen S. Abdullah, and Mohammad N. Fadhil. "Voice recognition system using machine learning techniques." Materials Today: Proceedings (2021).

Guido, Rodrigo Capobianco, et al. "CWT× DWT× DTWT× SDTWT: Clarifying terminologies and roles of different types of wavelet transforms." International Journal of Wavelets, Multiresolution and Information Processing 18.06 (2020): 2030001.

Barburiceanu, Stefania, Romulus Terebes, and Serban Meza "3D texture feature extraction and classification using GLCM and LBP-based descriptors " Applied Sciences 11 5 (2021): 2332.

Taylor L (2017) What is data justice? The case for connecting digital rights and freedoms globally. Big Data & Society 2017: 1–14.

Turow J (2021) The Voice Catchers: How Marketers Listen In to Exploit Your Feelings, Your Privacy, and Your Wallet. New Haven: Yale University Press.

D. a. a. tawisi (2017),”voiceprint its features and use” , Arab journal for security studies and training.

Alegre F, Soldi G and Evans N (2014) Evasion and obfuscation in automatic speaker verification. In: ICASSP, IEEE international conference on acoustics, speech and signal processing - proceedings, Florence, Italy, 4–9 May 2014, pp.749–753.

Amoore L (2020) Cloud Ethics: Algorithms and the Attributes of Ourselves and Others. Durham: Duke University Press. Andrejevic M (2012) Exploitation in the data mine. In: Fuchs C, Boersma K, Albrechtslund A and Sandoval M (eds) Internet Jansen et al. 11 and Surveillance. New York and London: Routledge, pp.91– 108.

Valentino-DeVries J (2020) How the police use facial recognition, and where it falls short. New York Times, 12 January

Ponraj, Abraham Sudharson. "Speech Recognition with Gender Identification and Speaker Diarization." 2020 IEEE International Conference for Innovation in Technology (INOCON). IEEE, 2020.

Botchkarev, Alexei. "Performance metrics (error measures) in machine learning regression, forecasting and prognostics: Properties and typology." arXiv preprint arXiv:1809.03006 (2018).

Mustafa, Wan Azani, et al. "Image enhancement based on discrete cosine transforms (DCT) and discrete wavelet transform (DWT): A review." IOP Conference Series: Materials Science and Engineering. Vol. 557. No. 1. IOP Publishing, 2019.

Kofman A (2018) Interpol rolls out international voice identification database using samples from 192 law enforcement agencies. The Intercept, 25 June. Leese M (2020) Fixing state vision: Interoperability, biometrics, and identity management in the EU. Geopolitics: 1–21.

Alegre F, Soldi G and Evans N (2014) Evasion and obfuscation in automatic speaker verification. In: ICASSP, IEEE international conference on acoustics, speech and signal processing - proceedings, Florence, Italy, 4–9 May 2014, pp.749–753

Karen wan,(2009),” the use of multimedia in education : design – production – evaluation” Dar al-Shuaa for publishing and science halb, Syrian.

Z. R. Tawfiq, "Voice Based Authentication Using Artificial Neural Network ", Software Engineering science, Iraqi Commission for Computers and Informatics, IRAQ, 2012.