Text Dependent Speaker Recognition using Deep Neural Networks - Tapa blanda

Suthar, Anilkumar

 
9783659921711: Text Dependent Speaker Recognition using Deep Neural Networks
Tapa blanda
ISBN 10: 3659921718 ISBN 13: 9783659921711
Editorial: LAP LAMBERT Academic Publishing, 2018

Sinopsis

Speaker Recognition is used for identification of a person depending on the characteristics contained in the speech signal. In this paper we propose the use of Deep Neural Network (DNN) for text dependent speaker Recognition system (SRS). Mel Frequency Cepstral Coefficients (MFCC) and Auto-encoder (Butterfly Structure Neural Network) are used to extract the features of speech signal at the initial stage. The previously obtained coefficients are then used to train the DNN to later classify the speakers. DNN can be directly used to extract features and classify speakers but the MFCC and Auto-encoder are used initially for data compression and maximum number of feature extraction thus aiming to get better efficiency and faster results.

"Sinopsis" puede pertenecer a otra edición de este libro.

Reseña del editor

Speaker Recognition is used for identification of a person depending on the characteristics contained in the speech signal. In this paper we propose the use of Deep Neural Network (DNN) for text dependent speaker Recognition system (SRS). Mel Frequency Cepstral Coefficients (MFCC) and Auto-encoder (Butterfly Structure Neural Network) are used to extract the features of speech signal at the initial stage. The previously obtained coefficients are then used to train the DNN to later classify the speakers. DNN can be directly used to extract features and classify speakers but the MFCC and Auto-encoder are used initially for data compression and maximum number of feature extraction thus aiming to get better efficiency and faster results.

"Sobre este título" puede pertenecer a otra edición de este libro.

Editorial
LAP LAMBERT Academic Publishing
Año de publicación
2018
Idioma
Inglés
ISBN 10 
3659921718
ISBN 13 
9783659921711
Encuadernación
Tapa blanda
Número de páginas
52
Editor
Kansara K.
Contacto del fabricante
no disponible
Persona responsable
no disponible