arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.17136cs.SDcs.AI
收藏

设备引导的音乐转移

Device-Guided Music Transfer

Singapore Management University(新加坡管理大学);University of Melbourne(墨尔本大学)

Manh Pham Hung, Changshuo Hu, Ting Dang, Dong Ma

AI总结:

DeMT通过提取扬声器频率响应曲线生成设备嵌入,实现跨设备的音乐风格迁移与鲁棒适应。

摘要:

设备引导的音乐转移通过适应未见过的设备来调整播放,以满足那些没有这些设备的用户需求。现有方法主要集中在修改音色、节奏、和声或乐器以模仿流派或艺术家,忽略了播放设备(即扬声器)多样的硬件属性。因此,我们提出了DeMT,它使用视觉语言模型将扬声器的频率响应曲线作为折线图进行处理,以提取设备嵌入。这些嵌入随后通过特征级线性调制条件化混合变压器。在自收集的数据集上微调后,DeMT能够实现有效的扬声器风格转移和对未见过的设备的鲁棒少样本适应,支持设备风格增强和质量提升等应用。

英文摘要:

Device-guided music transfer adapts playback across unseen devices for users who lack them. Existing methods mainly focus on modifying the timbre, rhythm, harmony, or instrumentation to mimic genres or artists, overlooking the diverse hardware properties of the playback device (i.e., speaker). Therefore, we propose DeMT, which processes a speaker's frequency response curve as a line graph using a vision-language model to extract device embeddings. These embeddings then condition a hybrid transformer via feature-wise linear modulation. Fine-tuned on a self-collected dataset, DeMT enables effective speaker-style transfer and robust few-shot adaptation for unseen devices, supporting applications like device-style augmentation and quality enhancement.

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。

↑