Can I read Adaptive Boosted Random Forest-support Vector Machine Based Classification Scheme for Speaker Identification on EtoBox?

Adaptive Boosted Random Forest-support Vector Machine Based Classification Scheme for Speaker Identification by Karthikeyan V; Suja Priyadharsini S is a Computer Science article available to read on EtoBox.

What is Adaptive Boosted Random Forest-support Vector Machine Based Classification Scheme for Speaker Identification about?

At each integrated work stage, many technologies and algebraic formulations are required to identify the speakers from speech signals. Due to advancements in machine learning and artificial intelligence, speaker recognition technologies are gaining popularity and are being used in a variety of applications. This paper presents a multi-feature adaptive boosted hybrid random forest support vector machine (AB-RFSVM) model that can process real-time, uninterrupted speech with 98 percent accuracy. To build the speaker recognition model, the extracted temporal and spectral speaker-specific information was applied as a feature vector to a suggested hybrid machine learning classifier. The goal of this work is to enhance the RF-SVM classifier’s categorization performance by adaptively boosting the decision of RFSVM. SVM moves around the decision trees positioned in the experimentally discovered subareas around the hyperplane dividing the multi-classes of correctly and incorrectly identified speakers is subject to boosting of classification decisions collected using the RFSVM classifier. The predetermined default configuration value was utilized while building the RFSVM classifier. Finally,

Who reads Adaptive Boosted Random Forest-support Vector Machine Based Classification Scheme for Speaker Identification?

Author

Karthikeyan V; Suja Priyadharsini S

Publisher

Elsevier BV

Published

2022

Language

EN

Field

Computer Science (Physical Sciences)