Low-Variance Multitaper MFCC Features: A Case Study in Robust Speaker Verification
The vocal training is useful for beginners to learn how to correctly sing, and for professional singers to tune their voice and expand their frequency range. In the paper, we propose a study on vocal training by analyzing voice pitch on android platform. Vocal training requires a vocal coach who is always besides you to correct your mistakes. However, beginner who wants to learn singing for fun or professional singer who practices his vocal technique everyday rather needs a short-hand assistance to control his or her singing. The proposed method is divided into four parts, such as preprocessing, feature extraction, feature matching and result output, that enables to perform efficient voice recognition. In addition, we describe the various training options of the proposed method, including several statistical analyses in order to describe the user’s progress in later stages.