arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.01248cs.SDcs.LGcs.MMeess.AS
收藏

一个轻量级的音乐纹理传输系统

A Lightweight Music Texture Transfer System

Beijing Advanced Innovation Center for Big Data and Brain Computing(北京大数据与脑计算高精尖创新中心);Beihang University(北京航空航天大学)

Xutan Peng, Chen Li, Zhi Cai, Faqiang Shi, Yidan Liu, Jianxin Li

摘要:

针对图像和文本转换问题的深度学习研究引起了人们的极大关注。然而,目前使用神经网络进行音乐特征传递的方法离实际应用还很远。在本文中,我们提出了一种新的系统,用于传输音乐的纹理,并将其作为一个开源项目发布。其核心算法由一个将声音表示为纹理谱的转换器、一个相应的重构器和一个前馈传输网络组成。我们从多个角度对该系统进行了评估,实验结果表明,它在声音效果和计算性能方面都取得了令人信服的结果。

英文摘要:

Deep learning researches on the transformation problems for image and text have raised great attention. However, present methods for music feature transfer using neural networks are far from practical application. In this paper, we initiate a novel system for transferring the texture of music, and release it as an open source project. Its core algorithm is composed of a converter which represents sounds as texture spectra, a corresponding reconstructor and a feed-forward transfer network. We evaluate this system from multiple perspectives, and experimental results reveal that it achieves convincing results in both sound effects and computational performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑