Speaker verification on small datasets with ResNet50

Manfron, Enrico; Minetto, Rodrigo; Teixeira, João Paulo

http://hdl.handle.net/10198/36716

Utilize este identificador para referenciar este registo.

Nome:	Descrição:	Tamanho:	Formato:
Camara_Ready_405_ICMTT.pdf		357.24 KB	Adobe PDF	Ver/Abrir

Contacte-nos

Autores

Manfron, Enrico

Minetto, Rodrigo

Teixeira, João Paulo

Resumo(s)

In this study, we explore the capabilities of speaker recognition technology for biometric authentication, developing speaker recognitionbased access control systems, and serving as a resource for future research. We focused on developing and evaluating the ResNet50 model for speaker verification. The model was trained and tested on private datasets with 32 speakers and public datasets with 1251 to 6112 speakers. The model ResNet50 achieved a good result on our private dataset by achieving the best EER of 0.7%.

URI

http://hdl.handle.net/10198/36716

Citação

Manfron, Enrico; Minetto, Rodrigo; Teixeira, João Paulo (2024). Speaker verification on small datasets with ResNet50. In International Conference on Management, Tourism and Technologies, ICMTT 2024. p. 41-50. ISBN 978-303174824-0. DOI: 10.1007/978-3-031-74825-7_5