20 papers
Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
Yonghyun Park, Chieh-Hsin Lai, Satoshi Hayakawa +7
While diffusion models excel at image generation, their growing adoption raises critical concerns about copyright issues and model transparency. Existing attribution methods identi…
LLM2Fx-Tools: Tool Calling For Music Post-Production
Seungheon Doh, Junghyun Koo, Marco A. MartÃnez-RamÃrez +5
This paper introduces LLM2Fx-Tools, a multimodal tool-calling framework that generates executable sequences of audio effects (Fx-chain) for music post-production. LLM2Fx-Tools uses…
SteerMusic: Enhanced Musical Consistency for Zero-shot Text-guided and Personalized Music Editing
Xinlei Niu, Kin Wai Cheuk, Jing Zhang +8
Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing me…
Automatic Music Mixing using a Generative Model of Effect Embeddings
Eloi Moliner, Marco A. MartÃnez-RamÃrez, Junghyun Koo +5
Music mixing involves combining individual tracks into a cohesive mixture, a task characterized by subjectivity where multiple valid solutions exist for the same input. Existing au…
Towards Blind Data Cleaning: A Case Study in Music Source Separation
Azalea Gui, Woosung Choi, Junghyun Koo +5
The performance of deep learning models for music source separation heavily depends on training data quality. However, datasets are often corrupted by difficult-to-detect artifacts…
Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior
Chin-Yun Yu, Marco A. MartÃnez-RamÃrez, Junghyun Koo +3
Style Transfer with Inference-Time Optimisation (ST-ITO) is a recent approach for transferring the applied effects of a reference audio to an audio track. It optimises the effect p…