|
Depot Institutionnel de l'UMBB >
Mémoires de Master 2 >
Institut de Génie Electrique et d'Electronique >
Telecommunication >
Veuillez utiliser cette adresse pour citer ce document :
http://dlibrary.univ-boumerdes.dz:8080/handle/123456789/9369
|
| Titre: | Speaker recongnition using neural network |
| Auteur(s): | Souihel, Dhouelkefel
Mehiri, Abdelouahab
Dahimene, A. |
| Mots-clés: | Speaker recongnition : history and development
Neural network |
| Date de publication: | 2018 |
| Résumé: | Speaker recognition is a biometric operation to determine the identity of the
speaker based on speech sample. Speaker recognition mainly divided into speaker
identification and speaker verification.
In this project, based on signal processing concept; the preprocessing using a voice activated detector (VAD) algorithm is applied and Mel frequency cepstral coefficient (MFCC) is used for the feature extraction, feed-forward artificial neural network is used as a classifier with one hidden layer and two. The system is tested for 11 speakers. For speaker identification, an average identification rate of 94% is achieved with one hidden layer and dropped to 63.1 % in two hidden layers. For speaker verification, an average verification of 100% is achieved. |
| Description: | 49 p. |
| URI/URL: | http://dlibrary.univ-boumerdes.dz:8080/handle/123456789/9369 |
| Collection(s) : | Telecommunication
|
Fichier(s) constituant ce document :
|
Tous les documents dans DSpace sont protégés par copyright, avec tous droits réservés.
|
