English(EN) G-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement

新的SG-Mamba模型通过稀疏图和Mamba增强视听语音

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-17 04:00

研究人员开发了SG-Mamba，一个新颖的轻量级视听语音增强框架。该模型集成了稀疏异构图和Mamba骨干网络，以提高跨模态对齐精度，同时保持计算效率。SG-Mamba明确建模了模态特定关系和长程时间上下文，在LRS3等数据集上取得了有竞争力的性能，并在嘈杂环境中表现出鲁棒性。 AI

影响引入了一种新的模型架构，在语音增强任务中平衡了效率和准确性。

排序理由该集群描述了一篇关于一种新颖的视听语音增强模型的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于一种新颖的视听语音增强模型的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Guo-Ruei Tseng, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen · 2026-09-17 04:00

G-Mamba：稀疏图引导的 Mamba 用于视听语音增强

arXiv:2609.18009v1 Announce Type: cross Abstract: Lightweight audio-visual speech enhancement (AVSE) models face a critical trade-off between computational efficiency and cross-modal alignment accuracy. While simple concatenation lacks relational expressiveness, dense cross-atten…