相关论文: ArtiFree: Detecting and Reducing Generative Artifa…

Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution for improving SV performance when handling short-duration…

Diffusion models are a new class of generative models that have recently been applied to speech enhancement successfully. Previous works have demonstrated their superior performance in mismatched conditions compared to state-of-the art…

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the…

Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditional distributions in the generative process and efficient computation of the loss as independent terms…

Non-autoregressive (NAR) text generation has attracted much attention in the field of natural language processing, which greatly reduces the inference latency but has to sacrifice the generation accuracy. Recently, diffusion models, a class…

Diffusion has emerged as a powerful framework for generative modeling, achieving remarkable success in applications such as image and audio synthesis. Enlightened by this progress, we propose a novel diffusion-based approach for symbolic…

Estimating causal effects from observational data is inherently challenging due to the lack of observable counterfactual outcomes and even the presence of unmeasured confounding. Traditional methods often rely on restrictive, untestable…

In this work, we address the challenge of generalizable audio deepfake detection (ADD) across diverse speech synthesis paradigms-including conventional text-to-speech (TTS) systems and modern diffusion or flow-matching (FM) based…

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…

Different from many other attributes, facial expression can change in a continuous way, and therefore, a slight semantic change of input should also lead to the output fluctuation limited in a small scale. This consistency is important.…

The generative aspect model is an extension of the multinomial model for text that allows word probabilities to vary stochastically across documents. Previous results with aspect models have been promising, but hindered by the computational…

The rapid advancement of generative image models has transformed digital media to the point where AI generated images can no longer be reliably distinguished from authentic photographs by human observers or many conventional detection…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Proper guidance strategies are essential to achieve high-quality generation results without retraining diffusion and flow-based text-to-image models. Existing guidance either requires specific training or strong inductive biases of…

Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…

In the domains of image and audio, diffusion models have shown impressive performance. However, their application to discrete data types, such as language, has often been suboptimal compared to autoregressive generative models. This paper…

Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically trained on limited datasets and evaluated under narrow…

Second-pass rescoring is employed in most state-of-the-art speech recognition systems. Recently, BERT based models have gained popularity for re-ranking the n-best hypothesis by exploiting the knowledge from masked language model…

We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, variational auto-encoders, are usually considered as…

Text-based image editing, powered by generative diffusion models, lets users modify images through natural-language prompts and has dramatically simplified traditional workflows. Despite these advances, current methods still suffer from a…