Catalogue des ouvrages Université de Laghouat
A partir de cette page vous pouvez :
Détail de l'auteur
Auteur Mohamed Elbachir Khelifi
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier Faire une suggestion Affiner la recherche
| Titre : | Automatic Arabic Speech Recognition by CNN | | Type de document : | document multimédia | | Auteurs : | Ali Elhocine Sefari, Auteur ; Mohamed Elbachir Khelifi, Auteur ; Safouane Chellali, Directeur de thèse | | Editeur : | Laghouat : Université Amar Telidji - Département d'électronique | | Année de publication : | 2023 | | Importance : | 75p. | | Note générale : | Option : Réseaux et Télécommunications | | Langues : | Français | | Résumé : | Automatic speech recognition has been an active field of study since the 1950s,
which explains its richness but also its difficulty. It involves the collaboration of multiple
disciplines and techniques. The complexity of the speech signal, resulting from the
interaction between sound production and perception by the ear, contributes to the
challenge of automatic speech recognition, which has become a highly interesting
research topic.
The objective of this thesis is the acquisition and implementation of a database
consisting of 20 phrases divided in to two categories connected words and separated
words, along with a corpus of syntactically and semantically correct sentences. This
database was recorded under real conditions, and the acoustic analysis of this database
was performed using the MFCC method, providing us with a series of input vectors for
the implemented Automatic Speech Recognition (ASR) system. This system is based on
Convolutional Neural Networks. Evaluating the performance of the ASR system using
the database analysis method will highlight the influence of parameterization. | | note de thèses : | Mémoire de master en électronique |
Automatic Arabic Speech Recognition by CNN [document multimédia] / Ali Elhocine Sefari, Auteur ; Mohamed Elbachir Khelifi, Auteur ; Safouane Chellali, Directeur de thèse . - Laghouat : Université Amar Telidji - Département d'électronique, 2023 . - 75p. Option : Réseaux et Télécommunications Langues : Français | Résumé : | Automatic speech recognition has been an active field of study since the 1950s,
which explains its richness but also its difficulty. It involves the collaboration of multiple
disciplines and techniques. The complexity of the speech signal, resulting from the
interaction between sound production and perception by the ear, contributes to the
challenge of automatic speech recognition, which has become a highly interesting
research topic.
The objective of this thesis is the acquisition and implementation of a database
consisting of 20 phrases divided in to two categories connected words and separated
words, along with a corpus of syntactically and semantically correct sentences. This
database was recorded under real conditions, and the acoustic analysis of this database
was performed using the MFCC method, providing us with a series of input vectors for
the implemented Automatic Speech Recognition (ASR) system. This system is based on
Convolutional Neural Networks. Evaluating the performance of the ASR system using
the database analysis method will highlight the influence of parameterization. | | note de thèses : | Mémoire de master en électronique |
|
Réservation
Réserver ce document
Exemplaires
| Disponibilité |
|---|
| Thc 09-22 | Thc 09-22 | CD | BIBLIOTHEQUE DE FACULTE DE TECHNOLOGIE | théses (tec) | Disponible |
