PianoBench: Evaluating Musical Perception and Reasoning in Language Models
cs.SD, cs.AI, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/zfturbo/music-source-separation-training
Terminology
Sources
- Flamingo: a Visual Language Model for Few-Shot Learning
- Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling
- Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
- Hybrid Spectrogram and Waveform Source Separation
- Gemma 4 Technical Report
- Music Flamingo: Scaling Music Understanding in Audio Language Models
- Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
- Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
- Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
- GiantMIDI-Piano: A large-scale MIDI dataset for classical piano music
- Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
- Unified Audio Intelligence Without Regressing on Text Intelligence
- MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
- Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
- MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark
- Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST
- Benchmarks and leaderboards for sound demixing tasks
- Music I Care About: Automated Multimodal Benchmarking of LLM Music Perception Skills on (Almost) Any Music
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems