REVIEW 8 cited by
Fast Timing-Conditioned Latent Audio Diffusion
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
Fast Timing-Conditioned Latent Audio Diffusion
read the original abstract
Generating long-form 44.1kHz stereo audio from text prompts can be computationally demanding. Further, most previous works do not tackle that music and sound effects naturally vary in their duration. Our research focuses on the efficient generation of long-form, variable-length stereo music and sounds at 44.1kHz using text prompts with a generative model. Stable Audio is based on latent diffusion, with its latent defined by a fully-convolutional variational autoencoder. It is conditioned on text prompts as well as timing embeddings, allowing for fine control over both the content and length of the generated music and sounds. Stable Audio is capable of rendering stereo signals of up to 95 sec at 44.1kHz in 8 sec on an A100 GPU. Despite its compute efficiency and fast inference, it is one of the best in two public text-to-music and -audio benchmarks and, differently from state-of-the-art models, can generate music with structure and stereo sounds.
Forward citations
Cited by 8 Pith papers
-
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
An entropy-based log-barrier on DiT outputs acts as an online curriculum in supervised diffusion fine-tuning, producing higher thematic development and textural diversity than standard training on MusicCaps.
-
Omni2Sound: Towards Unified Video-Text-to-Audio Generation
A single DiT-based diffusion model unifies video-to-audio, text-to-audio, and joint video-text-to-audio generation, supported by a new 470k-pair dataset and three-stage progressive training that resolves task competition.
-
How Do Diffusion Classifiers Decide? A Bias-Centric Evaluation
Diffusion classifiers show lower attribute-misbinding CAB than OpenCLIP but larger size-order gaps and background-driven accuracy drops, traced to pixel-aggregated reconstruction error and cross-attention routing.
-
OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
A jointly trained audio-video VAE with segment-level contrastive alignment and semantic distillation improves downstream text-to-audio-video synchronization and quality.
-
OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation
Jointly training audio and video VAEs with segment contrastive loss and semantic distillation yields more learnable, cross-aligned latents that improve downstream joint generation quality and sync.
-
Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models
DDE introduces a compact coordinator network that combines denoised outputs from pre-trained diffusion models to enable generation in larger domains and complex conditioning settings.
-
Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models
Causal probing of attention in audio separation transformers identifies dual pathways and asynchronous convergence, enabling a training-free Layer-Selective Attention Caching method that reduces self-attention computa...
-
Woosh: A Sound Effects Foundation Model
Woosh is a new publicly released foundation model optimized for high-quality sound effect generation from text or video, showing competitive or better results than open alternatives like Stable Audio Open.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.