The paper introduces MusICA-MetaBench, a framework for deriving on-demand music perception benchmarks from user-provided data, ensuring statistically reliable model comparisons.

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 introduces a maintainable hybrid architecture for generating harmonies from melodies using quantum-inspired exploration and rule-based optimization.

The paper introduces MusTBENCH, a new benchmark, and MusT, an optimization recipe, to rigorously test and improve the ability of Large Audio-Language Models (LALMs) to accurately ground their musical…

This paper introduces MeloDISinger, a text-based singing voice editing model that preserves melody and duration while enabling melody-aware duration control.

This paper proposes a framework for creating low-latency, interactive generative music AI using distillation in a streaming autoregressive latent space and music-aware consistency objectives.

The paper proposes a novel multimodal framework for session-based music recommendation that jointly models audio, lyric, and semantic content signals within a unified LLM-based sequential reasoning sy…

The paper presents aria, a dependency-free runtime for generating text-to-music using Stable Audio 3 on commodity hardware, with a focus on quantization for memory savings and activation steering.

This paper introduces WanSong, a diffusion-based model for long-form, commercial-grade song generation that directly generates high-fidelity, multilingual songs up to 5 minutes and outputs dual stems,…

This paper proposes RPPNet, a two-stage deep learning architecture for music generation with variable structural boundaries, which automatically derives grouping of Rhythm-Pitch Primitive sequences fr…

The paper introduces MADB, a large-scale dataset and benchmark for music aesthetic assessment with 9,999 tracks annotated by 30 trained annotators across 10 perceptual dimensions.

This paper introduces CODA, a real-time score following system that exploits the cascaded structure of music scores for prediction consistency and enables recovery from score discontinuities.

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.

This paper presents the structure of infinite melodic lines with self-similarity under all rational and irrational tempo ratios, allowing for infinite solutions in table canons.

The paper develops a general framework for dynamic consistent submodular maximization, achieving constant-factor approximations with sublinear consistency for both cardinality and rank-$k$ matroid con…

The paper introduces Noise-Aware BEATs (NABEATs), a noise-aware audio self-supervised learning framework that estimates clean BEATs representations from noisy audio signals using an auxiliary referenc…