Proposes an attribution-aware compensation framework for generative music that derives closed-form payments from catalog-level attribution informativeness and quantifies welfare effects under competition.
hub
Stable Audio Open
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
abstract
Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
MeanFlow applied in latent space enables true one-step Token2Wav generation with up to 17x RTF improvement and negligible quality loss versus multi-step baselines.
ArtifactNet extracts codec residuals from spectrograms with a 4M-parameter network to detect AI music at F1=0.9829 and 1.49% FPR on unseen tracks from 22 generators, outperforming larger baselines.
Moshi is the first real-time full-duplex spoken large language model that casts dialogue as speech-to-speech generation using parallel audio streams and an inner monologue of time-aligned text tokens.
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.
A curation pipeline combining diffusion-based synthetic mixtures with a discriminative classifier produces and releases FSD50K-Solo, a single-source subset of FSD50K that matches human expert labels on a test set.
Audio-Omni unifies audio understanding, generation, and editing in one end-to-end model across domains, backed by a new million-pair AudioEdit dataset, and achieves strong benchmark results.
GPC learns a motion vocabulary via Finite Scalar Quantization and end-to-end RL, then trains an autoregressive transformer for next-token control generation, achieving 99.98% motion reproduction success with emergent robustness.
A distilled multimodal diffusion model generates audio from text, video, or audio in four steps with claimed superior quality and ~25× fewer function evaluations.
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 computation by ~25% with negligible quality loss.
UniVoice is a conditional flow matching model with a Diffusion Transformer backbone that unifies TTS and SVS via modality-specific encoders and a null melody token for speech, achieving 5.26% speech PER and 16.22% singing PER.
Auxiliary lyric and timbre branches improve instrumental text-to-music generation quality in a controlled DiT setting even with degenerate inputs, outperforming parameter-reallocated depth variants and external baselines in objective and MOS evaluations.
Stochastic generative dynamics are decomposed into transport and osmotic parts via b_t = u_t + d_t, with Bridge Matching proposed to learn the components for controllable sampling.
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.
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.
citing papers explorer
-
What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music
Proposes an attribution-aware compensation framework for generative music that derives closed-form payments from catalog-level attribution informativeness and quantifies welfare effects under competition.
-
One-Step Token-to-Waveform Generation with MeanFlow in Latent Space
MeanFlow applied in latent space enables true one-step Token2Wav generation with up to 17x RTF improvement and negligible quality loss versus multi-step baselines.
-
ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics
ArtifactNet extracts codec residuals from spectrograms with a 4M-parameter network to detect AI music at F1=0.9829 and 1.49% FPR on unseen tracks from 22 generators, outperforming larger baselines.
-
Moshi: a speech-text foundation model for real-time dialogue
Moshi is the first real-time full-duplex spoken large language model that casts dialogue as speech-to-speech generation using parallel audio streams and an inner monologue of time-aligned text tokens.
-
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.
-
FSD50K-Solo: Automated Curation of Single-Source Sound Events
A curation pipeline combining diffusion-based synthetic mixtures with a discriminative classifier produces and releases FSD50K-Solo, a single-source subset of FSD50K that matches human expert labels on a test set.
-
Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
Audio-Omni unifies audio understanding, generation, and editing in one end-to-end model across domains, backed by a new million-pair AudioEdit dataset, and achieves strong benchmark results.
-
GPC: Large-Scale Generative Pretraining for Transferable Motor Control
GPC learns a motion vocabulary via Finite Scalar Quantization and end-to-end RL, then trains an autoregressive transformer for next-token control generation, achieving 99.98% motion reproduction success with emergent robustness.
-
AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation
A distilled multimodal diffusion model generates audio from text, video, or audio in four steps with claimed superior quality and ~25× fewer function evaluations.
-
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 computation by ~25% with negligible quality loss.
-
UniVoice: A Unified Model for Speech and Singing Voice Generation
UniVoice is a conditional flow matching model with a Diffusion Transformer backbone that unifies TTS and SVS via modality-specific encoders and a null melody token for speech, achieving 5.26% speech PER and 16.22% singing PER.
-
Instrumental Text-to-Music Generation with Auxiliary Conditioning Branches
Auxiliary lyric and timbre branches improve instrumental text-to-music generation quality in a controlled DiT setting even with degenerate inputs, outperforming parameter-reallocated depth variants and external baselines in objective and MOS evaluations.
-
Deterministic Decomposition of Stochastic Generative Dynamics
Stochastic generative dynamics are decomposed into transport and osmotic parts via b_t = u_t + d_t, with Bridge Matching proposed to learn the components for controllable sampling.
-
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.
-
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.
- Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path