pith. sign in

arxiv: 2205.05448 · v2 · pith:DSCSPUJLnew · submitted 2022-05-10 · 💻 cs.SD · cs.AI· cs.LG· eess.AS

Symphony Generation with Permutation Invariant Language Model

classification 💻 cs.SD cs.AIcs.LGeess.AS
keywords musicsymphonygenerationmodellanguagenovelproposesymbolic
0
0 comments X
read the original abstract

In this work, we propose a permutation invariant language model, SymphonyNet, as a solution for symbolic symphony music generation. We propose a novel Multi-track Multi-instrument Repeatable (MMR) representation for symphonic music and model the music sequence using a Transformer-based auto-regressive language model with specific 3-D positional embedding. To overcome length overflow when modeling extra-long symphony tokens, we also propose a modified Byte Pair Encoding algorithm (Music BPE) for music tokens and introduce a novel linear transformer decoder architecture as a backbone. Meanwhile, we train the decoder to learn automatic orchestration as a joint task by masking instrument information from the input. We also introduce a large-scale symbolic symphony dataset for the advance of symphony generation research. Empirical results show that the proposed approach can generate coherent, novel, complex and harmonious symphony as a pioneer solution for multi-track multi-instrument symbolic music generation.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Text2Score: Generating Sheet Music From Textual Prompts

    cs.SD 2026-05 unverdicted novelty 7.0

    A two-stage framework uses an LLM to plan musical structures from text and then generates conditioned ABC notation sheet music, outperforming baselines in expert-validated evaluations.

  2. ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence

    cs.SD 2026-04 unverdicted novelty 7.0

    ONOTE is a multi-format benchmark that applies a deterministic pipeline to expose a disconnect between perceptual accuracy and music-theoretic comprehension in leading omnimodal AI models.

  3. Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation

    cs.SD 2026-04 unverdicted novelty 7.0

    Anchored Cyclic Generation uses anchor features from known music to mitigate error accumulation in autoregressive models, with the Hi-ACG framework delivering better long-sequence symbolic music and music completion p...

  4. Libretto: Giving LLM Agents a Sense of Musical Structure

    cs.SD 2026-06 unverdicted novelty 6.0

    Libretto is a new agent-facing symbolic music framework that equips LLMs with explicit grammar and corpus-calibrated statistical axes to enable measurable generation, gap-filling, morphing, and self-revision.

  5. Rubato: Transcribing Piano Music with Timestamps

    cs.SD 2026-05 unverdicted novelty 6.0

    Rubato model with InterMo representation outperforms cascade methods in generating timestamped piano sheet music from audio, even when cascades receive ground-truth MIDI.