Pith. sign in

REVIEW 14 cited by

Noise2Music: Text-conditioned Music Generation with Diffusion Models

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 2302.03917 v2 pith:K24QXMRZ submitted 2023-02-08 cs.SD cs.LGeess.AS

classification cs.SDcs.LGeess.AS
keywords textmodelsaudiodiffusiongenerateintermediatemusicnoise2music
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce Noise2Music, where a series of diffusion models is trained to generate high-quality 30-second music clips from text prompts. Two types of diffusion models, a generator model, which generates an intermediate representation conditioned on text, and a cascader model, which generates high-fidelity audio conditioned on the intermediate representation and possibly the text, are trained and utilized in succession to generate high-fidelity music. We explore two options for the intermediate representation, one using a spectrogram and the other using audio with lower fidelity. We find that the generated audio is not only able to faithfully reflect key elements of the text prompt such as genre, tempo, instruments, mood, and era, but goes beyond to ground fine-grained semantics of the prompt. Pretrained large language models play a key role in this story -- they are used to generate paired text for the audio of the training set and to extract embeddings of the text prompts ingested by the diffusion models. Generated examples: https://google-research.github.io/noise2music

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

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

  1. Qwen-Music Technical Report

    cs.SD 2026-07 conditional novelty 6.0 of 10

    Qwen-Music generates high-fidelity vocal songs via 25 Hz semantic tokens, Melody-CoT planning, and DiT rendering, claiming SOTA on 13/16 metrics and expert preference over proprietary systems.

  2. Anysynth:Zero-Shot Instrument Cloning via In-Context Learning and Asymmetric Hierarchical Guidance

    cs.SD 2026-07 conditional novelty 6.0 of 10

    A zero-shot instrument cloning system feeds raw reference audio into a flow-matching DiT and uses asymmetric CFG to keep melody and timbre control separate.

  3. Dance to Music Generation leveraging Pre-training with Unpaired data and Contrastive Alignment

    cs.SD 2026-07 conditional novelty 6.0 of 10

    Beat-guided contrastive alignment of pretrained MotionBERT/MERT features plus ControlNet conditioning of AudioLDM improves dance–music alignment on AIST++ over a MusicGen textual-inversion baseline while remaining com...

  4. Unified Audio Intelligence Without Regressing on Text Intelligence

    cs.CL 2026-07 conditional novelty 6.0 of 10

    A unified 30B MoE audio-text LLM achieves state-of-the-art audio understanding, generation, and speech tasks while preserving text reasoning comparable to its text-only backbone.

  5. DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization

    eess.AS 2025-07 conditional novelty 6.0 of 10

    DiffRhythm+ improves full-length lyric-to-song generation via balanced data scaling, MuLan-based multimodal style control, and DPO fine-tuning guided by automated aesthetic scorers.

  6. Hear-Your-Click: Interactive Object-Specific Video-to-Audio Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A new interactive method lets users click on an object in a video and generates audio for just that object, using mask-conditioned contrastive fine-tuning and latent diffusion.

  7. MusGO: A Community-Driven Framework For Assessing Openness in Music-Generative AI

    cs.SD 2025-07 conditional novelty 6.0 of 10

    MusGO is a community-refined framework with 13 openness categories, applied to 16 music-generative models to produce a public openness leaderboard.

  8. DefFusionNet: Learning Multimodal Goal Shapes for Deformable Object Manipulation via a Diffusion-based Probabilistic Model

    cs.RO 2025-06 conditional novelty 6.0 of 10

    DefFusionNet learns a conditional diffusion model over goal point clouds for deformable shape servoing, enabling diverse multimodal goals and outperforming DefGoalNet with fewer demonstrations.

  9. Diff-TONE: Timestep Optimization for iNstrument Editing in Text-to-Music Diffusion Models

    cs.SD 2025-06 conditional novelty 6.0 of 10

    Diff-TONE selects the prompt-swap timestep using a distilled latent instrument classifier, improving content preservation over fixed timestep baselines in text-to-music diffusion editing.

  10. Video-Guided Text-to-Music Generation Using Public Domain Movie Collections

    cs.SD 2025-06 conditional novelty 6.0 of 10

    OSSL is the first self-hosted, mood-annotated video-music dataset, and a video adapter on MusicGen-Medium improves film music generation over text-only baselines.

  11. Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation

    cs.SD 2025-06 conditional novelty 6.0 of 10

    Under matched training conditions, auto-regressive models slightly outperform flow-matching on music quality and temporal control, while flow-matching offers faster inference and better inpainting flexibility.

  12. MusiChat: Vibe Composing for Music Creation

    cs.AI 2026-07 conditional novelty 5.0 of 10

    MusiChat enables iterative, structure-preserving music editing through natural-language conversation by layering an LLM-based interface over a deterministic symbolic music engine.

  13. ASTAR-NTU solution to AudioMOS Challenge 2025 Track1

    cs.SD 2025-07 conditional novelty 5.0 of 10

    DORA-MOS, a dual-branch MuQ/RoBERTa model with cross-attention and Gaussian label softening, achieved the top system-level SRCC of 0.991 for MI and 0.952 for TA on the AudioMOS 2025 Track 1 test set.

  14. FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration

    cs.SD 2026-07 reject novelty 4.0 of 10

    FlowSonic combines deterministic rectified-flow inversion, cached cross-attention injection, and a 'seeded' third-order Adams-Bashforth solver to report better timbre and genre edits on small datasets.

Pith tools