.png){kind=icon}
.png){kind=icon}
Return
Music Genre Classification Based on Functional Data Analysis
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3512874.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Music genre classification (MGC) has gained significant attention due to its broad applications in music information retrieval. Traditional MGC approaches often rely on hand-crafted features or deep learning models that may overlook the continuous and complex nature of audio signals. This paper proposes a noval method for MGC using functional data analysis (FDA) to represent music signals as smooth functions, capturing their temporal and harmonic properties more naturally. Then, adaptive Fourier decomposition (AFD) is used to extract meaningful coefficients from these functional representations, which are subsequently classified using a support vector machine (SVM). We evaluate our approach on two widely-used datasets: GTZAN and FMA_small. The experimental results show that our proposed method outperforms other compared methods in MGC.
Keywords:
Multiple signal classification
Feature extraction
Support vector machines
Music
Splines (mathematics)
Harmonic analysis
Mel frequency cepstral coefficient
Market research
Machine learning algorithms
Complexity theory
Adaptive Fourier decomposition
functional data analysis
music genre classification
support vector machine