Accomplishments

Combined Evidence of MFCC and CRP Features Using Machine Learning Algorithms for Singer Identi¯cation


  • Details
  • Share
Category
Articles
Authors
Publisher
World Scientific Company
Publishing Date
01-Jul-2020
volume
35
Issue
1
Pages
2158001-2158021
  • Abstract

Singer identification is a challenging task in music information retrieval because of the combined instrumental music with the singing voice. The previous approaches focus on identification of singers based on individual features extracted from the music clips. The objective of this work is to combine Mel Frequency Cepstral Coe±cients (MFCC) and Chroma DCT-reduced Pitch (CRP) features for singer identification system (SID) using machine learning techniques. The proposed system has mainly two phases. In the feature extraction phase, MFCC, MFCC, MFCC and CRP features are extracted from the music clips. In the identi¯cation phase, extracted features are trained with Bidirectional Long Short-Term Memory (BLSTM)-based Recurrent Neural Networks (RNN) and Convolution Neural Networks (CNN) and tested to identify different singer classes. The identi¯cation accuracy and Equal Error Rate (EER) are used as performance measures. Further, the experiments also demonstrate the effectiveness of score level fusion of MFCC and CRP feature in the singer identification system. Also, the experimental results are compared with the baseline system using support vector machines (SVM).