Publicação
Speaker recognitionin door access control system
| 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 |
| 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. |
|---|