arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.14856eess.AScs.IRcs.MMcs.SD
收藏

用于乐谱、音频和歌词的无监督生成对抗对齐表示

Unsupervised Generative Adversarial Alignment Representation for Sheet music, Audio and Lyrics

National Institute of Informatics(国立信息学研究所);SOKENDAI(综合研究大学院大学)

Donghuo Zeng, Yi Yu, Keizo Oyama

摘要:

乐谱、音频和歌词是创作歌曲的三种主要形式。在本文中,我们提出了一种无监督的生成对抗对齐表示(UGAAR)模型来学习三种主要音乐形式共享的深度判别表示:乐谱,歌词和音频,其中基于三个分支的深度神经网络架构被联合训练。特别是,该模型可以通过学习潜在共享子空间中的相关性,将音频和乐谱之间的强关系转移到音频-歌词和乐谱-歌词对。我们应用音频和乐谱的CCA组件来建立新的地面实况。生成(G)模型学习两对转移对的相关性,以针对固定歌词生成新的音频片对来挑战判别(D)模型。判别模型的目的是区分来自生成模型的输入还是来自基础事实的输入。这两个模型同时以对抗的方式进行训练,以增强深度对齐表示学习的能力。我们的实验结果表明,我们提出的UGAAR对齐表示学习之间的乐谱,音频和歌词的可行性。

英文摘要:

Sheet music, audio, and lyrics are three main modalities during writing a song. In this paper, we propose an unsupervised generative adversarial alignment representation (UGAAR) model to learn deep discriminative representations shared across three major musical modalities: sheet music, lyrics, and audio, where a deep neural network based architecture on three branches is jointly trained. In particular, the proposed model can transfer the strong relationship between audio and sheet music to audio-lyrics and sheet-lyrics pairs by learning the correlation in the latent shared subspace. We apply CCA components of audio and sheet music to establish new ground truth. The generative (G) model learns the correlation of two couples of transferred pairs to generate new audio-sheet pair for a fixed lyrics to challenge the discriminative (D) model. The discriminative model aims at distinguishing the input which is from the generative model or the ground truth. The two models simultaneously train in an adversarial way to enhance the ability of deep alignment representation learning. Our experimental results demonstrate the feasibility of our proposed UGAAR for alignment representation learning among sheet music, audio, and lyrics.

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。

↑