paper-with-me

Papers

Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement

2024-09-15 · Yudong Yang, Zhan Liu, Wenyi Yu, Guangzhi Sun, Qiuqiang Kong, Chao Zhang

Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While these models generalize well to unseen acoustic environments, they may not achieve the same level of fidelity as the discriminative models specifically trained to enhance particular acoustic conditions. In this paper, we propose Ex-Diff, a novel score-based diffusion model that integrates the latent representations produced by a discriminative model to improve speech and vocal enhancement, which combines the strengths of both generative and discriminative models. Experimental results on the widely used MUSDB dataset show relative improvements of 3.7% in SI-SDR and 10.0% in SI-SIR compared to the baseline diffusion model for speech and vocal enhancement tasks, respectively. Additionally, case studies are provided to further illustrate and analyze the complementary nature of generative and discriminative models in this context.

📄 PDF Abstract BibTeX arXiv:2409.09642

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising

2024-06-28 · Zhenhao Li, Huichi Zhou, Marek Rei, Lucia Specia

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models,…

Adversarial DefenseDenoising

Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning

2025-09-04 · Yifu Luo, Yongzhe Chang, Xueqian Wang arxiv

Diffusion probability models have shown significant promise in offline reinforcement learning by directly modeling trajectory sequences. However, existing approaches primarily focus on time-domain features while overlook…

Reinforcement Learning

DifFUSER: Diffusion Model for Robust Multi-Sensor Fusion in 3D Object Detection and BEV Segmentation

2024-04-06 · Duy-Tho Le, Hengcan Shi, Jianfei Cai, Hamid Rezatofighi

Diffusion models have recently gained prominence as powerful deep generative models, demonstrating unmatched performance across various domains. However, their potential in multi-sensor fusion remains largely unexplored.…

3D Object DetectionBEV SegmentationDenoisingobject-detection+2

DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model

2024-05-04 · Liangqi Lei, Keke Gai, Jing Yu, Liehuang Zhu

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright track…

R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization

2024-01-01 · CVPR 2024 1 · Kennard Yanting Chan, Fayao Liu, Guosheng Lin, Chuan Sheng Foo 외

Recently the authors of Zero-1-to-3 demonstrated that a latent diffusion model pretrained with Internet-scale data can not only address the single-view 3D object reconstruction task but can even attain SOTA results i…

3D Object ReconstructionNovel View SynthesisObject Reconstruction