Music Generation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

33 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 33 until expanded.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 190 papers with code (386 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Music Transformer
  12 Sep 2018 12 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 1 pointer-only (licence)
  This is impractical for long sequences such as musical compositions since their memory complexity for intermediate relative information is quadratic in the sequence length.
• Simple and Controllable Music Generation
  8 Jun 2023 8 repositories listed Syntology ran 11 of 18 samples · 7 unverified · 7 pointer-only (licence)
  We tackle the task of conditional music generation.
• MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
  19 Sep 2017 8 repositories listed
  The three models, which differ in the underlying assumptions and accordingly the network architectures, are referred to as the jamming model, the composer model and the hybrid model.
• It's Raw! Audio Generation with State-Space Models
  20 Feb 2022 6 repositories listed Syntology ran 6 of 6 samples · 0 unverified · 4 pointer-only (licence)
  SaShiMi yields state-of-the-art performance for unconditional waveform generation in the autoregressive setting.
• MusicLM: Generating Music From Text
  26 Jan 2023 5 repositories listed Syntology ran 6 of 16 samples · 10 unverified
  We introduce MusicLM, a model generating high-fidelity music from text descriptions such as "a calming violin melody backed by a distorted guitar riff".
• BigVGAN: A Universal Neural Vocoder with Large-Scale Training
  9 Jun 2022 5 repositories listed Syntology ran 8 of 17 samples · 9 unverified · 1 pointer-only (licence)
  Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous…
• Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs
  7 Jan 2021 5 repositories listed Syntology ran 3 of 9 samples · 6 unverified
  In this paper, we present a conceptually different approach that explicitly takes into account the type of the tokens, such as note types and metric types.
• MelNet: A Generative Model for Audio in the Frequency Domain
  4 Jun 2019 5 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps.
• This Time with Feeling: Learning Expressive Musical Performance
  10 Aug 2018 5 repositories listed
  Music generation has generally been focused on either creating scores or interpreting them.
• Mustango: Toward Controllable Text-to-Music Generation
  14 Nov 2023 4 repositories listed Syntology ran 7 of 9 samples · 2 unverified
  Through extensive experiments, we show that the quality of the music generated by Mustango is state-of-the-art, and the controllability through music-specific text prompts greatly outperforms other models such as…
• Counterpoint by Convolution
  18 Mar 2019 4 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  Machine learning models of music typically break up the task of composition into a chronological process, composing a piece of music in a single pass from beginning to end.
• Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
  29 Oct 2018 4 repositories listed
  Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales.
• MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
  31 Mar 2017 4 repositories listed
  We conduct a user study to compare the melody of eight-bar long generated by MidiNet and by Google's MelodyRNN models, each time using the same priming melody.
• Moûsai: Text-to-Music Generation with Long-Context Latent Diffusion
  27 Jan 2023 3 repositories listed
  Recent years have seen the rapid development of large generative models for text; however, much less research has explored the connection between text and another "language" of communication -- music.
• MMM : Exploring Conditional Multi-Track Music Generation with the Transformer
  13 Aug 2020 3 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  We propose the Multi-Track Music Machine (MMM), a generative system based on the Transformer architecture that is capable of generating multi-track music.
• Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation
  25 Apr 2018 3 repositories listed Syntology ran 0 of 35 samples · 35 unverified
  Experimental results show that using binary neurons instead of HT or BS indeed leads to better results in a number of objective measures.
• A Critical Review of Recurrent Neural Networks for Sequence Learning
  29 May 2015 3 repositories listed
  Recurrent neural networks (RNNs) are connectionist models that capture the dynamics of sequences via cycles in the network of nodes.
• Vision-to-Music Generation: A Survey
  27 Mar 2025 2 repositories listed
  Vision-to-music Generation, including video-to-music and image-to-music tasks, is a significant branch of multimodal artificial intelligence demonstrating vast application prospects in fields such as film scoring, short…
• Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance
  23 Sep 2024 2 repositories listed
  The complex nature of musical emotion introduces inherent bias in both recognition and generation, particularly when relying on a single audio encoder, emotion classifier, or evaluation metric.
• FakeMusicCaps: a Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Models
  16 Sep 2024 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We evaluate the proposed dataset by performing initial experiments regarding the detection and attribution of TTM-generated audio.
• FLUX that Plays Music
  1 Sep 2024 2 repositories listed Syntology ran 6 of 9 samples · 3 unverified · 9 pointer-only (licence)
  This paper explores a simple extension of diffusion-based rectified flow Transformers for text-to-music generation, termed as FluxMusic.
• MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation
  21 Jul 2024 2 repositories listed
  However, textual prompts alone cannot precisely control temporal musical features such as chords and rhythm of the generated music.
• Quality-aware Masked Diffusion Transformer for Enhanced Music Generation
  24 May 2024 2 repositories listed Syntology ran 4 of 7 samples · 3 unverified
  Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation.
• Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models
  16 May 2024 2 repositories listed Syntology ran 10 of 12 samples · 2 unverified
  A cascaded diffusion model is trained to model the hierarchical language, where each level is conditioned on its upper levels.
• COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
  25 Apr 2024 2 repositories listed Syntology ran 2 of 5 samples · 3 unverified · 5 pointer-only (licence)
  We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples.
• JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models
  9 Aug 2023 2 repositories listed
  Despite the task's significance, prevailing generative models exhibit limitations in music quality, computational efficiency, and generalization.
• MuseCoco: Generating Symbolic Music from Text
  31 May 2023 2 repositories listed
  In contrast, symbolic music offers ease of editing, making it more accessible for users to manipulate specific musical elements.
• Byte Pair Encoding for Symbolic Music
  27 Jan 2023 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  When used with deep learning, the symbolic music modality is often coupled with language model architectures.
• Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task
  21 Nov 2022 2 repositories listed
  Benefiting from large-scale datasets and pre-trained models, the field of generative models has recently gained significant momentum.
• ComMU: Dataset for Combinatorial Music Generation
  17 Nov 2022 2 repositories listed
  Commercial adoption of automatic music composition requires the capability of generating diverse and high-quality music suitable for the desired context (e.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.