ConcateNet：基于局部与全局特征拼接的对话分离
ConcateNet: Dialogue Separation Using Local And Global Feature Concatenation
AI总结：
针对广播等场景的对话分离需求，提出基于局部与全局特征拼接的ConcateNet模型，在域内降噪数据集上性能具竞争力，在域外广播数据集上泛化能力优于现有降噪SOTA方法。
摘要：
对话分离指从混合信号（如电影或电视节目）中分离出对话信号，是广播相关应用中实现对话增强的必要步骤。本文提出用于对话分离的ConcateNet，其基于一种处理局部与全局特征的新方法，旨在提升对域外信号的泛化能力。ConcateNet使用聚焦降噪的公开数据集训练，在三个数据集上评估：两个聚焦降噪的数据集（域内）显示ConcateNet性能具有竞争力，一个聚焦广播的数据集（域外）验证了所提架构相比所考量的现有降噪SOTA方法具有更优的泛化性能。
英文摘要：
Dialogue separation involves isolating a dialogue signal from a mixture, such as a movie or a TV program. This can be a necessary step to enable dialogue enhancement for broadcast-related applications. In this paper, ConcateNet for dialogue separation is proposed, which is based on a novel approach for processing local and global features aimed at better generalization for out-of-domain signals. ConcateNet is trained using a noise reduction-focused, publicly available dataset and evaluated using three datasets: two noise reduction-focused datasets (in-domain), which show competitive performance for ConcateNet, and a broadcast-focused dataset (out-of-domain), which verifies the better generalization performance for the proposed architecture compared to considered state-of-the-art noise-reduction methods.
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。
