Anzeige
Erschienen in:
2015 | OriginalPaper | Buchkapitel
An Artificial Neural Networks Model by Using Wavelet Analysis for Speaker Recognition
verfasst von : Kanaka Durga Returi, Y. Radhika
Erschienen in: Information Systems Design and Intelligent Applications
Verlag: Springer India
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
An Artificial Neural Networks Model by using Wavelet Analysis for Speaker Recognition has been presented in this paper. The wavelet analysis was used to extract the features. These extracted features were trained using Artificial Neural Networks with popular Back Propagation Learning Algorithm. In this analysis of testing, the speakers speak out the same set of words, with these set words the features were extracted and fed into the training of the neural network. The neural network notifies the identity of the speaker. In order to test the system, the voice data of the speakers were recorded. The experiments were carried out by using 800 data sets of total 40 individual speakers. For each of these speakers, 20 speech signals were used for training. All these signals were used for training, validation and testing. This approach reveals that the overall performance of system is 95 %.