EConv-TasNet：高效Conv-TasNet用于有效语音分离
EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation
浏览论文内容
中文总结 AI 辅助
提出eConv-TasNet，通过分组早期拆分和多组特征聚合模块，在减少22.4%参数、提升18.9%推理速度的同时，SI-SNRi提高14.0%-28.0%，实现高效语音分离。
中文摘要 AI 辅助
Conv-TasNet一直是时域语音分离的强基线，许多研究通过双路径网络、U-Net和注意力机制等先进架构对其进行了扩展。然而，这些方法往往引入高计算成本和复杂度，限制了它们在资源受限场景中的部署。为解决这一问题，我们提出了eConv-TasNet，一种Conv-TasNet的高效变体，在不依赖资源密集型模块的情况下同时提升了有效性和效率。所提出的模型包含一个分组早期拆分（GES）模块和一个多组特征聚合（MGFA）模块。GES在中间阶段生成具有判别性的说话人嵌入，而MGFA逐步聚合这些组级表示，以进行精细的掩码估计。实验结果表明，eConv-TasNet在三个公共基准上将模型大小减少了22.4%，推理速度提升了18.9%，SI-SNRi提高了14.0%-28.0%。此外，与最先进的方法相比，它在显著减少参数和降低推理成本的同时，取得了具有竞争力的性能。这些结果展示了在边缘部署中有利的效率-效果权衡。
英文摘要
Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.
发表机构
- Novatek Microelectronics Corporation（联咏科技股份有限公司）
机构由 AI 辅助整理，请以论文原文为准。
