CNN 기반 장르 소분류 모델을 활용한 실시간 음악 장르 분류 모델 연구

다국어 초록 (Multilingual Abstract)

In this paper, we propose an N-genre music classification model and ensemble models that can more accurately classify 10 music genres based on the proposed N-genre model. The GTZAN data set is used as the music data set, and different MFCC-based color maps are compared to identify the one that produces the best classification accuracy. Two methods of model learning are used: (i) using a 30 s long music image and (ii) using a 5 s long music image, wherein the latter utilizes the voting method. The classification accuracy of these two methods is compared. Among the various types of MFCC-based color maps, the gist-rainbow method with better classification accuracy is chosen, and the 3-genre classification model is actually selected among several N-genre classification models. Furthermore, ensemble models overlapped for four genres is proposed and their classification accuracies are compared. Ensemble Model II, using the voting method, obtains an accuracy of 92.0% for the GTZAN data set. The classification accuracy of the proposed ensemble model II is compared with the those of the other reported models.

목차 (Table of Contents)

• Abstract
• I. 서론
• II. 데이터 셋 및 특징 추출 방법
• III. N-장르 분류 모델 및 앙상블 모델 기반 음악 장르 분류기
• IV. 결론
• REFERENCES

참고문헌 (Reference)

1 배준, "소프트맥스를 이용한 딥러닝 음악장르 자동구분 투표 시스템" 한국정보통신학회 23 (23): 27-32, 2019

2 "matplotlib"

3 S. Sugianto, "Voting-Based music genre classification using melspectogram and convolutional neural network" 330-333, 2019

4 H. Lee, "Unsupervised feature learning for audio classification using convolutional deep belief networks" 1096-1104, 2009

5 B. L. Sturm, "The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use"

6 J. H. Foleis, "Texture selection for automatic music genre classification" 89 : 2020

7 D. Ghosal, "Musical genre and style reconstruction using deep neural networks and transfer learning" 1010-1018, 2018

8 D. Bisharad, "Music genre recognition using residual neural networks" 2063-2068, 2019

9 D. Bisharad, "Music genre recognition using convolutional recurrent neural network architecture" 2019

10 Y. Zhuang, "Music genre classification with transformer classifier" 155-159, 2020

11 B. Liang, "Music genre classification using transfer learning" 392-393, 2020

12 H. Bahuleyan, "Music genre classification using machine learning techniques"

13 C. P. Tang, "Music genre classification using a hierarchical long short term memory (LSTM) model" 2018

14 A. Elbir, "Music genre classification and music recommendation by using deep learning" 56 (56): 627-629, 2020

15 S. Oramas, "Multimodal deep learning for music genre classification" 1 (1): 4-21, 2018

16 "GTZAN Dataset"

17 "Ensemble learning"

18 J. Pons, "End-to-End learning for music audio tagging at scale" 637-644, 2018

19 조민근, "Convolutional Neural Network 기반실시간 자율 댄싱 로봇 시스템" 제어·로봇·시스템학회 23 (23): 373-382, 2017

20 김동훈, "CDBN 속성을 사용한 음악 장르 분류" 한국지능시스템학회 27 (27): 187-194, 2017

21 Y. M. G. Costa, "An evaluation of Convolutional Neural Networks for music classification using spectrograms" 52 : 28-38, 2016

22 Zehra Durdağ, "A New Genre Classification with the Colors of Music" Sakarya University Journal of Computer and Information Sciences 2 (2): 53-60, 2019