REVIEW 9 cited by
Anticipatory Music Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We introduce anticipation: a method for constructing a controllable generative model of a temporal point process (the event process) conditioned asynchronously on realizations of a second, correlated process (the control process). We achieve this by interleaving sequences of events and controls, such that controls appear following stopping times in the event sequence. This work is motivated by problems arising in the control of symbolic music generation. We focus on infilling control tasks, whereby the controls are a subset of the events themselves, and conditional generation completes a sequence of events given the fixed control events. We train anticipatory infilling models using the large and diverse Lakh MIDI music dataset. These models match the performance of autoregressive models for prompted music generation, with the additional capability to perform infilling control tasks, including accompaniment. Human evaluators report that an anticipatory model produces accompaniments with similar musicality to even music composed by humans over a 20-second clip.
Forward citations
Cited by 9 Pith papers
-
Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation
Controlled experiments show that a 10ms performance-timed token stream lowers Frechet Music Distance roughly twofold versus beat-grid tokens, across model sizes from 0.8B to 27B.
-
MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
Musical concepts are linearly decodable and steerable in two public text-to-MIDI models, with prediction forming gradually in an encoder-decoder and late in a vocabulary-extended LLM.
-
A Reproducible, Scalable Pipeline for Synthesizing Autoregressive Model Literature
A scalable literature-synthesis pipeline that retrieves, filters, extracts, summarizes, and converts AR-model papers into runnable training scripts, with F1 > 0.85 extraction and three reproduction case studies.
-
Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
Self-supervised pretraining on 60,000 hours of symbolic piano music produces a generative model and contrastive embeddings that beat leading baselines on continuation quality and several MIR classification benchmarks.
-
AI Harmonizer: Expanding Vocal Expression with a Generative Neurosymbolic Music AI System
A new offline system automatically adds three harmonized vocal parts to a solo melody using trained music AI models, but its claimed musical quality is not empirically evaluated.
-
Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling
Aria-MIDI contributes 1.19 million piano MIDI files (about 100,000 hours) transcribed from web audio through LLM-guided crawling, source-separation-based classification, and the Aria-AMT transcription model.
-
ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement
A corruption-refinement transformer, ImprovNet, generates controllable jazz and classical improvisations of complete piano pieces, and also handles harmonization, continuation, and infilling.
-
Local deployment of large-scale music AI models on commodity hardware
The authors port the Anticipatory Music Transformer to MLC and WebLLM, run it in a browser, and measure faster-than-real-time MIDI generation on Apple silicon.
-
TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization
TinyMusician distills MusicGen and applies hand-picked mixed-precision quantization to make a 1.04 GB on-device music generator, but the headline '93% quality, 55% smaller' claims conflict with the paper's own tables.
Discussion (0). Continue with ORCID to comment.