Publicação

Speaker recognitionin door access control system

Ver documento

Detalhes bibliográficos
Resumo:In this paper, we explore the potential of speaker recognition technology as a biometric authentication method for access control systems. We focus on the development and evaluation of two machine learning models, the Gaussian Mixture Model (GMM) and Multilayer Perceptron (MLP), for speaker identification. Our research presents a review of speaker recognition literature, followed by a detailed methodology for constructing and training the GMM and MLP models on a specific dataset. Experimental results highlight the performance of these models in terms of accuracy and efficiency. This study contributes to the application of GMM and MLP models for speaker recognition-based access control systems, serving as a resource for future research and development in secure and effective access control solutions.
Autores principais:Manfron, E.
Outros Autores:Teixeira, João Paulo; Mineto, R.
Ano:2023
País:Portugal
Tipo de documento:documento de conferência
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Bragança
Idioma:inglês
Origem:Biblioteca Digital do IPB
Descrição
Resumo:In this paper, we explore the potential of speaker recognition technology as a biometric authentication method for access control systems. We focus on the development and evaluation of two machine learning models, the Gaussian Mixture Model (GMM) and Multilayer Perceptron (MLP), for speaker identification. Our research presents a review of speaker recognition literature, followed by a detailed methodology for constructing and training the GMM and MLP models on a specific dataset. Experimental results highlight the performance of these models in terms of accuracy and efficiency. This study contributes to the application of GMM and MLP models for speaker recognition-based access control systems, serving as a resource for future research and development in secure and effective access control solutions.