相关论文: SRTNet: Time Domain Speech Enhancement Via Stochas…

Diffusion models are widely used for generative tasks across domains. Given a pre-trained diffusion model, it is often desirable to fine-tune it further either to correct for errors in learning or to align with downstream applications.…

Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…

Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These…

Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image…

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…

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…

In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conventional methods that utilize trimaps merely as loose…

Due to the unprecedented breakthroughs brought about by deep learning, speech enhancement (SE) techniques have been developed rapidly and play an important role prior to acoustic modeling to mitigate noise effects on speech. To increase the…

This paper introduces the first gradient-based framework for prompt optimization in text-to-image diffusion models. We formulate prompt engineering as a discrete optimization problem over the language space. Two major challenges arise in…

In recent years, the joint training of speech enhancement front-end and automatic speech recognition (ASR) back-end has been widely used to improve the robustness of ASR systems. Traditional joint training methods only use enhanced speech…

Scene text image super-resolution (STISR) aims at simultaneously increasing the resolution and readability of low-resolution scene text images, thus boosting the performance of the downstream recognition task. Two factors in scene text…

We describe a modulation-domain loss function for deep-learning-based speech enhancement systems. Learnable spectro-temporal receptive fields (STRFs) were adapted to optimize for a speaker identification task. The learned STRFs were then…

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

Despite pre-trained language models such as BERT have achieved appealing performance in a wide range of natural language processing tasks, they are computationally expensive to be deployed in real-time applications. A typical method is to…

This paper investigates how to improve the runtime speed of personalized speech enhancement (PSE) networks while maintaining the model quality. Our approach includes two aspects: architecture and knowledge distillation (KD). We propose an…

The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive,…

We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem. Rather than relying on iterative sampling, DriftSE natively achieves one-step inference by…

Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing…

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Speech signals in real-world environments are frequently affected by various distortions such as additive noise, reverberation, and bandwidth limitation, which may appear individually or in combination. Traditional speech enhancement…