Music Genre Classification Based on Functional Data Analysis
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 prop...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10781338/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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. |
|---|---|
| ISSN: | 2169-3536 |