arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00001eess.AScs.LGcs.SD
收藏

VaPar Synth --一种用于音频合成的变参数模型

VaPar Synth -- A Variational Parametric Model for Audio Synthesis

Indian Institute of Technology Bombay(印度理工学院孟买分校);ENS Paris-Saclay(巴黎-萨克雷高等师范学院)

Krishna Subramani, Preeti Rao, Alexandre D'Hooge

摘要:

随着数据驱动的统计建模和丰富的计算能力的出现,研究人员越来越多地转向深度学习来进行音频合成。这些方法试图直接在时域或频域中对音频信号进行建模。为了更灵活地控制所生成的声音,利用更直接地对应于诸如音高、动态和音色的音乐属性的信号的参数表示来工作可能更有用。我们提出了VaPar合成器-变分参数合成器,它利用一个条件变分自动编码器(CVAE)训练一个合适的参数表示。我们证明了我们提出的模型的能力,通过重建和生成的乐器音调灵活控制其音高。

英文摘要:

With the advent of data-driven statistical modeling and abundant computing power, researchers are turning increasingly to deep learning for audio synthesis. These methods try to model audio signals directly in the time or frequency domain. In the interest of more flexible control over the generated sound, it could be more useful to work with a parametric representation of the signal which corresponds more directly to the musical attributes such as pitch, dynamics and timbre. We present VaPar Synth - a Variational Parametric Synthesizer which utilizes a conditional variational autoencoder (CVAE) trained on a suitable parametric representation. We demonstrate our proposed model's capabilities via the reconstruction and generation of instrumental tones with flexible control over their pitch.

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。

↑