Pith. sign in

REVIEW 5 cited by

MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training

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

arxiv 2106.05630 v1 pith:GRMVE6AN submitted 2021-06-10 cs.SD cs.CLcs.IRcs.MMeess.AS

classification cs.SDcs.CLcs.IRcs.MMeess.AS
keywords musicsymbolicunderstandingclassificationmusicbertpre-trainingdatalarge-scale
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Symbolic music understanding, which refers to the understanding of music from the symbolic data (e.g., MIDI format, but not audio), covers many music applications such as genre classification, emotion classification, and music pieces matching. While good music representations are beneficial for these applications, the lack of training data hinders representation learning. Inspired by the success of pre-training models in natural language processing, in this paper, we develop MusicBERT, a large-scale pre-trained model for music understanding. To this end, we construct a large-scale symbolic music corpus that contains more than 1 million music songs. Since symbolic music contains more structural (e.g., bar, position) and diverse information (e.g., tempo, instrument, and pitch), simply adopting the pre-training techniques from NLP to symbolic music only brings marginal gains. Therefore, we design several mechanisms, including OctupleMIDI encoding and bar-level masking strategy, to enhance pre-training with symbolic music data. Experiments demonstrate the advantages of MusicBERT on four music understanding tasks, including melody completion, accompaniment suggestion, genre classification, and style classification. Ablation studies also verify the effectiveness of our designs of OctupleMIDI encoding and bar-level masking strategy in MusicBERT.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MixAssist: An Audio-Language Dataset for Co-Creative AI Assistance in Music Mixing

    cs.SD 2025-07 conditional novelty 7.0 of 10

    MixAssist is the first audio-grounded, multi-turn conversational dataset for co-creative music mixing instruction, and fine-tuning Qwen-Audio on it yields human-comparable mixing advice.

  2. MeloBottleneck: Self-Supervised Melody Skeleton Extraction with a Latent Subsequence Bottleneck

    cs.SD 2026-07 conditional novelty 6.0 of 10

    Self-supervised latent-subsequence bottlenecks extract coherent melody skeletons that transfer more robustly than pseudo-label note classifiers and improve ornament-robust retrieval.

  3. Scaling Self-Supervised Representation Learning for Symbolic Piano Performance

    cs.SD 2025-06 conditional novelty 6.0 of 10

    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.

  4. Large Language Models' Internal Perception of Symbolic Music

    cs.CL 2025-07 conditional novelty 5.0 of 10

    LLM-generated MIDI data carries enough genre and style signal to train above-chance classifiers and melody predictors, but far less than real music data.

  5. Workflow-Based Evaluation of Music Generation Systems

    eess.AS 2025-06 conditional novelty 5.0 of 10

    A single-producer workflow evaluation of eight music AI tools finds they work as idea and sound generators but not as complete composers, and proposes a reusable framework.

Pith tools