Related papers: GLA-Grad: A Griffin-Lim Extended Waveform Generati…

Large-scale 3D generative models require substantial computational resources yet often fall short in capturing fine details and complex geometries at high resolutions. We attribute this limitation to the inefficiency of current…

We propose a speech enhancement system that combines speaker-agnostic speech restoration with voice conversion (VC) to obtain a studio-level quality speech signal. While voice conversion models are typically used to change speaker…

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…

The data and compute requirements of current language modeling technology pose challenges for the processing and analysis of low-resource languages. Declarative linguistic knowledge has the potential to partially bridge this data scarcity…

We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…

Equipping a deep model the abaility of few-shot learning, i.e., learning quickly from only few examples, is a core challenge for artificial intelligence. Gradient-based meta-learning approaches effectively address the challenge by learning…

Collaborative filtering is a critical technique in recommender systems. It has been increasingly viewed as a conditional generative task for user feedback data, where newly developed diffusion model shows great potential. However, existing…

Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively generating its SID conditioned on the user's history. However,…

Recent generative-prior-based methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-quality faces either by single-stage latent optimization or…

We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensities to the generator's output and unlabeled reference text…

Diffusion models have emerged as powerful deep generative techniques, producing high-quality and diverse samples in applications in various domains including audio. While existing reviews provide overviews, there remains limited in-depth…

Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthesis. This paper proposes a linear diffusion model (LinDiff)…

Generative modeling offers new opportunities for bioacoustics, enabling the synthesis of realistic animal vocalizations that could support biomonitoring efforts and supplement scarce data for endangered species. However, directly generating…

We propose in this paper an analytically new construct of a diffusion model whose drift and diffusion parameters yield an exponentially time-decaying Signal to Noise Ratio in the forward process. In reverse, the construct cleverly carries…

Reward Feedback Learning (ReFL) has recently shown great potential in aligning model outputs with human preferences across various generative tasks. In this work, we introduce a ReFL framework, named DiffusionReward, to the Blind Face…

Generating the motion of orchestral conductors from a given piece of symphony music is a challenging task since it requires a model to learn semantic music features and capture the underlying distribution of real conducting motion. Prior…

Recent studies have shown that the denoising process in (generative) diffusion models can induce meaningful (discriminative) representations inside the model, though the quality of these representations still lags behind those learned…

Despite strong performance in data-rich regimes, deep learning often underperforms in the data-scarce settings common in practice. While foundation models (FMs) trained on massive datasets demonstrate strong generalization by extracting…

Masked diffusion models (MDMs) have achieved notable progress in modeling discrete data, while their potential in molecular generation remains underexplored. In this work, we explore their potential and introduce the surprising result that…

Despite a growing interest in diffusion-based language models, existing work has not shown that these models can attain nontrivial likelihoods on standard language modeling benchmarks. In this work, we take the first steps towards closing…