利用生成對抗網路產生音樂節奏遊戲譜面;Generation of Music Game Beatmap via Generative Adversarial Network

National Chung Cheng University Institutional Repository > 工學院 > 資訊工程學系 > 學位論文 > Item A095B0000Q/56

Please use this identifier to cite or link to this item: http://ccur.lib.ccu.edu.tw/handle/A095B0000Q/56

Title:	利用生成對抗網路產生音樂節奏遊戲譜面;Generation of Music Game Beatmap via Generative Adversarial Network
Authors:	王振翰;WANG, CHEN-HAN
Contributors:	資訊工程研究所
Keywords:	深度學習;卷積神經網路;生成對抗網路;Deep Learning;Convolutional Neural Networks;Generative Adversarial Networks
Date:	2018
Issue Date:	2019-05-23 10:30:19 (UTC+8)
Publisher:	資訊工程研究所
Abstract:	音樂節奏遊戲是目前非常熱門的遊戲，但設計遊戲譜面過於耗時，此外，現存生成譜面的方法也有許多限制，於是我們提出了基於生成對抗網路的方法產生音樂節奏遊戲譜面。首先，音樂被分離為人聲與配樂兩部分，這使我們產生的譜面更貼近真實的譜面。我們的模型包含兩種生成對抗網路的概念：為了加入音樂資訊而採用的Conditional Generative Adversarial Nets (CGANs)以及使模型更好收斂的Improved Wasserstein GAN (WGAN-GP)。我們比較了此方法以及其他條件下的實驗。我們也設計了問卷來衡量此方法的實驗結果，而此方法的實驗結果與真實的譜面得到的分數非常相近，也就是說，我們的實驗結果與真實譜面非常相似。 Music games are very popular now, but designing beatmaps usually takes too much time. In addition, there is some limitation of existing methods to generate beatmaps. In this thesis, beatmap generation method is proposed based on Generative Adversarial Networks (GANs). Audio is firstly separated into the vocal and instrument parts to make this method close to beatmap design philosophy of designers. Our model consists of Conditional Generative Adversarial Nets (CGANs) and Improved Wasserstein GAN (WGAN-GP) for considering audio information and fast convergency of model training. Our results are compared with different methods. Besides, we conduct a subjective evaluation of our results and the real beatmaps. Our results are very competitive to the real beatmaps which means our results are close to the real beatmaps.
Appears in Collections:	[資訊工程學系] 學位論文

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	366	View/Open

Loading...