LPC-based feature coefficients for voice authentication tasks
Article Sidebar
Main Article Content
Abstract
Voice authentication is a promising biometric technique based on extracting meaningful information from the speech signal using computing a vector of feature coefficients. Based on that, this paper evaluates the effectiveness of linear predictive coefficients when combined with other simple metrics in voice authentication tasks. Linear predictive coefficients were chosen due to their relatively good performance and not-so-complicated structures compared to similar alternatives. All the feature coefficients have been evaluated through an extensive parameter space study to apprehend the main limitations and potentials of voice authentication under different scenarios. A classifier based on artificial neural networks has been implemented for such an evaluation.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms: Authors retain the copyright and guarantee the journal the right to be the first publication of the work, as well as, licensed under a Creative Commons Attribution License that allows others share the work with an acknowledgment of the authorship of the work and the initial publication in this journal. Authors may separately establish additional agreements for the non-exclusive distribution of the version of the work published in the journal (for example, placing it in an institutional repository or publishing it in a book), with acknowledgment of its initial publication in this journal. Authors are allowed and encouraged to disseminate their work electronically (for example, in institutional repositories or on their own website) before and during the submission process, as it may lead to productive exchanges as well as further citation earliest and oldest of published works.