用文字控制生成与人声匹配的伴奏，精准适配乐器和风格。
Sing-On-Your-Beat: Simple Text-Controllable Accompaniment Generations
- 通过文本提示控制伴奏生成，实现风格与乐器的精确调节。
- 仅需10秒音频输入与文本描述，即可生成高质量伴奏。
- 适合音乐创作新手或需要快速生成伴奏的创作者使用。
歌唱是人类最珍视的娱乐形式之一。然而，创作一首优美歌曲需要与人声相辅相成、且符合特定乐器配置和音乐类型的伴奏。尽管深度学习发展推动了伴奏生成研究，但以往方法常难以精确对齐目标乐器与音乐风格。为此，本文提出一种简单有效的方法，通过文本提示实现对伴奏的精准控制，使生成音乐能与人声协调，并满足指定的乐器配置和音乐类型要求。通过大量实验，我们成功利用人声输入与文本指令生成了10秒长度的伴奏。
原文摘要 · Abstract (English)
Singing is one of the most cherished forms of human entertainment. However, creating a beautiful song requires an accompaniment that complements the vocals and aligns well with the song instruments and genre. With advancements in deep learning, previous research has focused on generating suitable accompaniments but often lacks precise alignment with the desired instrumentation and genre. To address this, we propose a straightforward method that enables control over the accompaniment through text prompts, allowing the generation of music that complements the vocals and aligns with the song instrumental and genre requirements. Through extensive experiments, we successfully generate 10-second accompaniments using vocal input and text control.
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。