허밍: DeepJ 구조를 이용한 이미지 기반 자동 작곡 기법 연구 = Humming: Image Based Automatic Music Composition Using DeepJ Architecture

다국어 초록 (Multilingual Abstract)

Thanks to the competition of AlphaGo and Sedol Lee, machine learning has received world-wide attention and huge investments. The performance improvement of computing devices greatly contributed to big data processing and the development of neural networks. Artificial intelligence not only imitates human beings in many fields, but also seems to be better than human capabilities. Although humans’ creation is still considered to be better and higher, several artificial intelligences continue to challenge human creativity. The quality of some creative outcomes by AI is as good as the real ones produced by human beings. Sometimes they are not distinguishable, because the neural network has the competence to learn the common features contained in big data and copy them. In order to confirm whether artificial intelligence can express the inherent characteristics of different arts, this paper proposes a new neural network model called Humming. It is an experimental model that combines vgg16, which extracts image features, and DeepJ's architecture, which excels in creating various genres of music. A dataset produced by our experiment shows meaningful and valid results. Different results, however, are produced when the amount of data is increased. The neural network produced a similar pattern of music even though it was a different classification of images, which was not what we were aiming for. However, these new attempts may have explicit significance as a starting point for feature transfer that will be further studied.

참고문헌 (Reference)

1 최희주 ; 황정훈 ; 류신혜 ; 김상욱, "그림의 색채 감정 효과를 기반으로 한 음악 생성 알고리즘" 한국멀티미디어학회 23 (23): 765-771, 2020

2 K. Simonyan, "Very Deep Convolutional Networks for Large-Scale Image Recognition"

3 S. Dieleman, "The Challenge of Realistic Music Generation : Modelling Raw Audio at Scale"

4 S. Hochreiter, "Long Short-Term Memory" 9 (9): 1735-1780, 1997

5 I. Goodfellow, "Generative Adversarial Nets" 2 : 2672-2680, 2014

6 D. D Johnson, "Generating Polyphonic Music using Tied Parallel Networks" Springer 128-143, 2017

7 H. H. Mao, "DeepJ:Style-Specific Music Generation" 377-382, 2018

8 J. P. Briot, "Deep Learning Techniques for Music Generation--A Survey"

9 D. Makris, "Combining LSTM and Feed Forward Neural Networks for Conditional Rhythm Composition" Springer 570-582, 2017

10 D. P. Kingma, "Auto-Encoding Variational Bayes"

11 D. Eck, "A First Look at Music Composition using LSTM Recurrent Neural Networks" 103 : 48-, 2002