Melody

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 18

All topics

CANTABILE: Learning Expressive Dynamics for Robotic Piano Performance
Sep 16, 2026Woosik Kim, Wonhyeok Choi, Sunghoon ImInstrument Beethoven
KAIST, Daejeon, Republic of Korea · DGIST, Daegu, Republic of Korea
MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation
Jul 29, 2026Wei-Jaw Lee, Hsuan-Yu Yeh, Ting-Yi Hu +3Singing Voice Conversion Melody
GICE, National Taiwan University
From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference
Jul 27, 2026Darina Gold, Alexander Schwirjow, Viktor Haag +4Small Large Language Models Efficient Inference
IIS Fraunhofer
Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering
Jul 22, 2026Junyu Dai, Xinyue Fan, Weiqin Li +14Song Generation Melody
Alibaba Token Foundry
ChartGenEval: Corruption-Tested Multi-Dimensional Feedback for Rhythm-Game Chart Generation
Jul 14, 2026Jhen-Ke LinMelody Stress Testing
National Yang Ming Chiao Tung University
MusicMark: A Robust Generative Watermarking Framework for Music Generation
Jul 13, 2026Seohwan Yun, Jeeyoung Yun, Yongjin Kim +2Multi-Bit Watermarking Watermarks
Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea · Department of Computer Engineering, Inha University, Incheon, Republic of Korea
MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck
Jul 11, 2026Fan Bu, Rongfeng Li, Linfeng FanMelody Skeleton
Beijing University of Posts and Telecommunications · Central Conservatory of Music
Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems
Jun 30, 2026Ashish Hallur, Thomas Thebaud, Georgi Tinchev +2Prosody Melody
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA · Amazon Inc., Seattle, WA, USA
MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling
Jun 29, 2026Yoonjeong Park, Jaekwon Im, Juhan NamSinging Voice Conversion Melody
Graduate School of Artificial Intelligence, KAIST, South Korea · Graduate School of Culture Technology, KAIST, South Korea
Mood-Aware Music Recommendation: Integrating User Affective Signals into Ranking Systems
Jun 11, 2026Terence Zeng, Abhishek K. UmrawalCollaborative Filtering Affective Computing
University of Illinois Urbana-Champaign, Urbana, Illinois 61801, USA
Diffusion-Based Heart Sound Generation: Evaluation with Physiological Signal Metrics, Classifiers, and Expert Listening
Jun 1, 2026Xinqi Bao, Jia Bi, Xin Chen +2Physiological Signals Hear
Department of Information Science & Engineering, KTH Royal Institute of Technology, Stockholm, 114 28 Sweden · Karolinska Institutet (KI), Stockholm, Sweden · Rutherford Appleton Laboratory, United Kingdom +2
BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation
May 26, 2026Yutong Wang, Yunke Wang, Xinyuan Chen +1Audio-Visual Consistency Melody
The University of Sydney · Shanghai AI Laboratory
STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
May 12, 2026Joshua OpriaMelody Keystroke Dynamics
Independent Researcher
Do Melody and Rhythm Coevolve?
May 7, 2026Harin Lee, Rainer Polak, Manuel Anglada-Tort +3Melody Cross-Cultural Variation
University of Cambridge, UK · RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Norway · Department of Psychology, Goldsmiths College, University of London, UK +3
From Beats to Breaches:How Offensive AI Infers Sensitive User Information from Playlists
May 6, 2026Stefano Cecconello, Mauro Conti, Luca Pajola +2Membership Inference Attacks Melody
University of Padova, Italy · Örebro University, Sweden · Spritz Matter, Italy
MindMelody: A Closed-Loop EEG-Driven System for Personalized Music Intervention
May 2, 2026Yimeng Zhang, Yueru Sun, Haoyu Gu +1Generative Music Melody
South China University of Technology, Guangzhou, China
YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance
Mar 25, 2026Chunbo Hao, Junjie Zheng, Guobin Ma +6Singing Voice Conversion Melody
AI Lab, Giant Network, China
Evolutionary modelling reveals melodic and harmonic constraints on global scale structure
Aug 22, 2024John M McBride, Steven Brown, Elizabeth Phillips +2Symbolic Music Generation Harmonization
Department of Physics, Ulsan National Institute of Science and Technology, South Korea · McMaster University, Canada · University of Auckland, New Zealand +1

Sep 16, 2026, cs.ROJ/K move · Enter open · S save

CANTABILE: Learning Expressive Dynamics for Robotic Piano Performance

Woosik Kim, Wonhyeok Choi, Sunghoon Im

KAIST, Daejeon, Republic of Korea · DGIST, Daegu, Republic of Korea

Instrument Beethoven Melody Expressivity Conditional Velocity

Open paper AskPDF arXiv

Robotic piano playing has emerged as a standard benchmark for dexterous bimanual manipulation, yet progress on it has been measured almost entirely by note accuracy -- which keys are pressed (pitch) and when (onset) -- leaving the musical dynamics essential for expressive performance neither rewarded nor evaluated. We propose CANTABILE, a dynamics-aware framework for robotic piano performance that (i) closes the score-to-contact loop by conditioning the policy on upcoming velocity goals and mapping each key's angular velocity at onset back to MIDI velocity, (ii) couples a velocity-fidelity reward with an onset-coverage reward, so that dynamics cannot be improved by omitting difficult notes, and (iii) refines a frozen dynamics-aware base policy with an alpha-scaled, finger-only residual that localizes strike-intensity adaptation away from nominal note execution. On EXPRESSIVE-51, a dynamics-rich 51-song subset of RoboPianist, CANTABILE raises Velocity F1 -- jointly measuring pitch, onset, and intensity within a +/-8 MIDI-velocity tolerance -- from 0.06 to 0.34 over the RoboPianist baseline, improves all 51 songs, more than halves matched-note velocity error, and reduces log-mel distance to reference audio by 8%. Intensity-randomized training further enables runtime control of performance intensity without retraining.

Momentum

Related topics

Latest papers 18