LatentFT uses latent-space Fourier transforms and frequency masking in diffusion autoencoders to enable timescale-specific manipulation of musical structure in generative models.
Noise2music: Text-conditioned music generation with diffusion models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
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
representative citing papers
Stylus achieves training-free music style transfer on Mel-spectrograms by repurposing image diffusion models via style-key injection in self-attention plus phase-preserving reconstruction, outperforming baselines by 34.1% in content preservation and 25.7% in perceptual quality per 2,925 human raters
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
A data-free streaming consistency distillation framework enables single-step autoregressive generation from text-to-music models for real-time interactive use while preserving timbre and rhythm via latent, spectral, and temporal losses.
JenBridge pretrains a flow-matching Transformer on text-audio data then adapts it with video conditioning and an LLM director to select transitions, claiming better coherence than prior methods on a new LVS benchmark.
S2Accompanist is a 402M-parameter semantic-aware diffusion model that achieves SOTA on the ATTM Grand Challenge benchmark for music accompaniment generation via automated data processing and structure-guided VAE fine-tuning.
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.
citing papers explorer
-
Latent Fourier Transform
LatentFT uses latent-space Fourier transforms and frequency masking in diffusion autoencoders to enable timescale-specific manipulation of musical structure in generative models.
-
Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms
Stylus achieves training-free music style transfer on Mel-spectrograms by repurposing image diffusion models via style-key injection in self-attention plus phase-preserving reconstruction, outperforming baselines by 34.1% in content preservation and 25.7% in perceptual quality per 2,925 human raters
-
Unified Audio Intelligence Without Regressing on Text Intelligence
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
-
Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation
A data-free streaming consistency distillation framework enables single-step autoregressive generation from text-to-music models for real-time interactive use while preserving timbre and rhythm via latent, spectral, and temporal losses.
-
JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions
JenBridge pretrains a flow-matching Transformer on text-audio data then adapts it with video conditioning and an LLM director to select transitions, claiming better coherence than prior methods on a new LVS benchmark.
-
S2Accompanist: A Semantic-Aware and Structure-Guided Diffusion Model for Music Accompaniment Generation
S2Accompanist is a 402M-parameter semantic-aware diffusion model that achieves SOTA on the ATTM Grand Challenge benchmark for music accompaniment generation via automated data processing and structure-guided VAE fine-tuning.
-
Shap-E: Generating Conditional 3D Implicit Functions
Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.
-
Movie Gen: A Cast of Media Foundation Models
A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.