arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.08702eess.AScs.AI
收藏

一种用于语音增强与修复的双分支并行网络

A Dual-Branch Parallel Network for Speech Enhancement and Restoration

Department of Electronic Engineering, Hanyang University(电子工程系,翰阳大学);Department of Artificial Intelligence, Hanyang University(人工智能系,翰阳大学)

Da-Hee Yang, Dail Kim, Joon-Hyuk Chang, Jeonghwan Choi, Han-gil Moon

AI总结:

DBP-Net通过双分支并行架构实现语音增强与修复的统一处理,利用参数共享和跨分支跳连提升性能,同时保持模型轻量。

摘要:

我们提出了一种新的通用语音修复模型DBP-Net(双分支并行网络),旨在有效处理包括噪声、回声和带宽退化在内的复杂现实干扰。与以往依赖单一处理路径或分别用于增强和修复的模型不同,DBP-Net引入了统一架构的双平行分支——一个基于掩码的分支用于干扰抑制,一个基于映射的分支用于频谱重建。DBP-Net的关键创新在于两个分支之间的参数共享和跨分支跳连,其中掩码分支的输出被显式融合到映射分支中。这种设计使DBP-Net能够在轻量级框架内同时利用互补的学习策略——抑制和生成。实验结果表明,DBP-Net在综合语音修复任务中显著优于现有基线模型,同时保持紧凑的模型大小。这些发现表明,DBP-Net为统一语音增强和修复提供了有效且可扩展的解决方案,适用于多样的干扰场景。

英文摘要:

We present a novel general speech restoration model, DBP-Net (dual-branch parallel network), designed to effectively handle complex real-world distortions including noise, reverberation, and bandwidth degradation. Unlike prior approaches that rely on a single processing path or separate models for enhancement and restoration, DBP-Net introduces a unified architecture with dual parallel branches-a masking-based branch for distortion suppression and a mapping-based branch for spectrum reconstruction. A key innovation behind DBP-Net lies in the parameter sharing between the two branches and a cross-branch skip fusion, where the output of the masking branch is explicitly fused into the mapping branch. This design enables DBP-Net to simultaneously leverage complementary learning strategies-suppression and generation-within a lightweight framework. Experimental results show that DBP-Net significantly outperforms existing baselines in comprehensive speech restoration tasks while maintaining a compact model size. These findings suggest that DBP-Net offers an effective and scalable solution for unified speech enhancement and restoration in diverse distortion scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑