Speaker Recognition System Using Htk
Résumé: The technological strives the world is witnessing as we speak made that biometric applications for security measures and authentication are being ubiquitous in every aspect of human life. These applications are turning out to be effective and efficient in other sectors, as forensics and surveillance. Research in the area of Biometrics is continuously being conducted and new methods ensuring better results and more accuracy are developed every day. In this respect, through this work we tried to implement a speaker recognition system by using a technique that proved to be powerful to model an important number of physical phenomena: Hidden Markov Modeling (HMM). In this work, we attempted to design a Text-Independent Speaker Recognizer using the HMM Toolkit (HTK). The system was simple and easy to build once the theory behind it was understood and put in practice. It was implemented using two different approaches, the first used a Left-to-Right HMM and the second used an Ergodic HMM. We obtained encouraging results with both HMM structures and concluded that HMMs are as efficient in speaker recognition as in speech recognition.
Mots-clès:
Nos services universitaires et académiques
Thèses-Algérie vous propose ses divers services d’édition: mise en page, révision, correction, traduction, analyse du plagiat, ainsi que la réalisation des supports graphiques et de présentation (Slideshows).
Obtenez dès à présent et en toute facilité votre devis gratuit et une estimation de la durée de réalisation et bénéficiez d'une qualité de travail irréprochable et d'un temps de livraison imbattable!
Aucun fichier associé
Si le fichier est volumineux, l'affichage peut échouer. Vous pouvez obtenir le fichier directement en cliquant sur le bouton "Télécharger".
