用深度学习生成符合风格的歌词，加速创作流程。
Optimizing the Songwriting Process: Genre-Based Lyric Generation Using Deep Learning Models
- 用分词技术将歌词拆解为独立段落进行训练
- 基线模型召回率更高，两种模型精确度相当
- 生成歌词语义清晰，能区分不同音乐风格
传统作词过程复杂耗时，难以高效产出契合特定风格的完整歌词。本项目基于18,000首Spotify歌曲数据集，开发了一种基于标记的独创预处理方法，将歌词解析为独立段落，并据此训练了基础预训练seq2seq模型和基于LSTM的神经网络模型。实验结果显示，基线模型在召回率（ROUGE）上表现更优，而两种模型的精确度（BLEU）相近。定性分析表明，生成歌词虽不完全复现原文，但语义可理解，且能明显区分所属音乐风格。整体结果证明，基于深度学习的歌词生成可有效加速创作流程，实现风格化输出。
原文摘要 · Abstract (English)
The traditional songwriting process is rather complex and this is evident in the time it takes to produce lyrics that fit the genre and form comprehensive verses. Our project aims to simplify this process with deep learning techniques, thus optimizing the songwriting process and enabling an artist to hit their target audience by staying in genre. Using a dataset of 18,000 songs off Spotify, we developed a unique preprocessing format using tokens to parse lyrics into individual verses. These results were used to train a baseline pretrained seq2seq model, and a LSTM-based neural network models according to song genres. We found that generation yielded higher recall (ROUGE) in the baseline model, but similar precision (BLEU) for both models. Qualitatively, we found that many of the lyrical phrases generated by the original model were still comprehensible and discernible between which genres they fit into, despite not necessarily being the exact the same as the true lyrics. Overall, our results yielded that lyric generation can reasonably be sped up to produce genre-based lyrics and aid in hastening the songwriting process.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。