Search papers, labs, and topics across Lattice.
National Cheng-Kung University {lisifei2022, yangli2022, weiming.dong}@ia.ac.cn Corresponding author. Abstract Cover songs constitute a vital aspect of musical culture, preserving the core melody of an original composition while reinterpreting it to infuse novel emotional depth and thematic emphasis. Although prior research has explored the reinterpretation of instrumental music through melody-conditioned text-to-music models, the task of cover song generation remains largely unaddressed. In this work, we reformulate our cover song generation as a conditional generation, which simultaneously generates new vocals and accompaniment conditioned on the original vocal melody and text prompts. To this end, we present SongEcho, which leverages Instance-Adaptive Element-wise Linear Modulation (IA-EiLM), a framework that incorporates controllable generation by improving both conditioning injection mechanism and conditional representation. To enhance the conditioning injection mechanism, we extend Feature-wise Linear Modulation (FiLM) to an Element-wise Linear Modulation (EiLM), to facilitate precise temporal alignment in melody control. For conditional representations, we propose Instance-Adaptive Condition Refinement (IACR), which refines conditioning features by interacting with the hidden states of the generative model, yielding instance-adaptive conditioning. Additionally, to address the scarcity of large-scale, open-source full-song datasets, we construct Suno70k, a high-quality AI song dataset enriched with comprehensive annotations. Experimental results across multiple datasets demonstrate that our approach generates superior cover songs compared to existing methods, while requiring fewer than 30%30\% of the trainable parameters. The code, dataset, and demos are available at https://github.com/lsfhuihuiff/SongEcho_ICLR2026. 1 Introduction If great melodies merit reinterpretation, then exceptional cover songs breathe new life into their originals. Cover songs play an essential role in musical culture, acting as conduits for cultural memory and agents in the formation of a musical canon. Iconic examples, such as Whitney Houston’s transformative rendition of Dolly Parton’s “I Will Always Love You”, reinterpret the style of the song, evolving a gentle country ballad into a worldwide anthem of deep affection 111https://www.youtube.com/shorts/PdE_dAkMDW4
2
0
4
GraspALL achieves 32-44% better garment grasping accuracy in low-light by adaptively fusing RGB and depth data based on a learned illumination intensity reference.
Generate impressive cover songs with fewer parameters: SongEcho uses a novel modulation technique to reinterpret existing melodies with new vocals and accompaniment, outperforming existing methods while using less compute.
