~ similar to 2607.27296· 19 results
A system called Profy uses weakly supervised learning to provide time-aligned highlights for piano practice, helping learners identify areas for improvement.
Ping Wang, Guang Yang, Nazif Can Tamer, Victoria Ebert +1 more
This paper evaluates the effectiveness of automatic music transcription systems using two complementary metrics: notation similarity to a reference score and playback similarity to the original perfor…
This paper introduces PianoKontext, a flow matching rendering model for classical piano music that generates variable-length performances.
Analyzing Beethoven's 'Moonlight Sonata' reveals distinct machine learning architectures
This paper proposes a method for learning a world model of piano sound using Joint Embedding Predictive Architectures (JEPA), treating music as an action-conditioned system.
The paper introduces MusICA-MetaBench, a framework for deriving on-demand music perception benchmarks from user-provided data, ensuring statistically reliable model comparisons.
The authors introduce SMEBench, a large-scale benchmark for evaluating neural music editing systems.
This paper proposes methods for unsupervised detection of AI-generated music in large-scale catalogs.
This paper investigates the effectiveness of parameter-efficient fine-tuning for adapting pretrained music encoders for multimodal music retrieval.
The paper introduces Reflector, an interactive audio workstation that adapts pitch-class retrieval as compositions evolve, using a learned embedding space based on a hand-designed oracle.
This paper compares three generative models for Bach-style piano music and their strengths and weaknesses.
The paper introduces the MPB Corpus, a comprehensive dataset of 500 Brazilian musical pieces encoded across four parameters, and presents methods for encoding and analyzing the data.
Sangheon Park, Seonguk Ju, Suin Chung, Danbinaerin Han +1 more
This paper introduces a 46-hour annotated dataset for Pansori, a traditional Korean vocal genre, and evaluates four input representations to detect shortcut learning. The models learn mode-relevant fe…