论文标题
自动神经歌词和旋律构图
Automatic Neural Lyrics and Melody Composition
论文作者
论文摘要
在本文中，我们提出了一种解决算法歌曲创作过程中最具挑战性的方面的技术，该过程使人类社区能够发现原始歌词和适合生成的歌词的旋律。提出的歌曲创作系统，自动神经歌词和旋律作曲（AutonLMC）是尝试使用人工神经网络自动创作自动创作的整个过程。我们的歌词至矢量（Lyric2Vec）模型在大量的抒情术配对数据集上进行了训练，该数据集在音节上解析，单词和句子级别是大规模嵌入模型，使我们能够训练数据驱动的模型，例如流行英语歌曲的循环神经网络。 AutonLMC是一个编码器二次的顺序复发性神经网络模型，该模型由抒情生成器，抒情编码器和经过旋律解码器训练有素的端到端组成。 AutonLMC旨在为业余爱好者或没有音乐知识的人自动生成歌词和相应的旋律。它还可以吸引专业歌词作家的歌词来产生匹配的旋律。定性和定量评估措施表明，所提出的方法确实能够生成原始歌词和相应的旋律来创作新歌。
In this paper, we propose a technique to address the most challenging aspect of algorithmic songwriting process, which enables the human community to discover original lyrics, and melodies suitable for the generated lyrics. The proposed songwriting system, Automatic Neural Lyrics and Melody Composition (AutoNLMC) is an attempt to make the whole process of songwriting automatic using artificial neural networks. Our lyric to vector (lyric2vec) model trained on a large set of lyric-melody pairs dataset parsed at syllable, word and sentence levels are large scale embedding models enable us to train data driven model such as recurrent neural networks for popular English songs. AutoNLMC is a encoder-decoder sequential recurrent neural network model consisting of a lyric generator, a lyric encoder and melody decoder trained end-to-end. AutoNLMC is designed to generate both lyrics and corresponding melody automatically for an amateur or a person without music knowledge. It can also take lyrics from professional lyric writer to generate matching melodies. The qualitative and quantitative evaluation measures revealed that the proposed method is indeed capable of generating original lyrics and corresponding melody for composing new songs.
