Please use this identifier to cite or link to this item: http://prr.hec.gov.pk/jspui/handle/123456789/17820
Title: Speaker Verification Service (SVS) Based on Voice Biometrics for Identification and Tracking
Authors: Ismail, Muhammad
Keywords: Computer & IT
Computer & IT
Issue Date: 2021
Publisher: University of Sindh, Jamshoro.
Abstract: At present, voice biometrics is commonly used for identification and authentication of users through their voice. Voice-based services such as mobile banking, access to personal devices, and logging into social networks are the common examples of authenticating users through voice biometrics. In Pakistan, voice-based services are very common in banking and mobile/cellular sector, however, these services do not use voice features to recognize customers. Therefore, the chance to use these services with false identity is always high. It is essential to design Voice-Based Systems (VBS) to minimize the risk of false identity. An important step in designing VBS i.e. speech and speaker recognition systems, is the voice database design. A comprehensive voice database plays significant role for design and development of VBS specifically designed for particular applications. In this work, we developed regional voice datasets for voice biometrics, by collecting voice dataset in different local accents of Pakistan. Although, there is a global need for voice biometrics especially when voice-based services are common, however, this work uses Pakistan as a use case to build regional voice dataset for voice biometrics. To build voice datasets, voice samples were recorded from 180 male and female speakers with two languages English and Urdu in form of five regional accents. Mel Frequency Cepstral Coefficients (MFCCs) were extracted from the collected voice samples and used to train Machine Learning (ML) models including Support Vector Machine (SVM), Multilayer Perceptron (ML), Random Forest (RF) and K-nearest neighbor (KNN). The results indicate that MLP outperformed SVM, RF and KNN by achieving 88.53% and 86.58% recognition accuracy on English language voice biometrics dataset and Urdu language voice biometrics dataset respectively.
Gov't Doc #: 23942
URI: http://prr.hec.gov.pk/jspui/handle/123456789/17820
Appears in Collections:PhD Thesis of All Public / Private Sector Universities / DAIs.

Files in This Item:
File Description SizeFormat 
Muhammad Ismail 2021 information Technology uni of sindh.pdfphd.Thesis3.33 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.