arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.22682eess.AS
收藏

SRP-PHAT-NET:一种面向混响扬声器定位的可靠性驱动深度神经网络

SRP-PHAT-NET: A Reliability-Driven DNN for Reverberant Speaker Localization

Ben-Gurion University of the Negev(内盖夫本-古里安大学)

Bar Shaybet, Vladimir Tourbabin, Boaz Rafaely

AI总结:

本文提出SRP-PHAT-NET,一种利用SRP-PHAT方向图并内置可靠性估计的深度神经网络,通过高斯加权标签训练实现可靠性评分,实验证明选择性使用高置信度预测可显著提升混响环境下的DOA定位精度。

摘要:

在混响环境中进行精确的到达方向(DOA)估计仍然是空间音频应用面临的一项基本挑战。尽管深度学习方法在此类条件下已展现出强劲性能,但它们通常缺乏评估其预测可靠性的机制——而这一特性对于实际部署至关重要。在本工作中,我们提出了SRP-PHAT-NET,一种深度神经网络框架,它利用SRP-PHAT方向图作为空间特征,并引入了内置的可靠性估计。为了实现有意义的可靠性评分,该模型使用以真实方向为中心的高斯加权标签进行训练。我们系统地分析了标签平滑对准确性和可靠性的影响,证明高斯核宽度的选择可根据具体应用需求进行调整。实验结果表明,选择性地使用高置信度预测可显著提高定位精度,凸显了将可靠性融入基于深度学习的DOA估计的实际益处。

英文摘要:

Accurate Direction-of-Arrival (DOA) estimation in reverberant environments remains a fundamental challenge for spatial audio applications. While deep learning methods have shown strong performance in such conditions, they typically lack a mechanism to assess the reliability of their predictions - an essential feature for real-world deployment. In this work, we present the SRP-PHAT-NET, a deep neural network framework that leverages SRP-PHAT directional maps as spatial features and introduces a built-in reliability estimation. To enable meaningful reliability scoring, the model is trained using Gaussian-weighted labels centered around the true direction. We systematically analyze the influence of label smoothing on accuracy and reliability, demonstrating that the choice of Gaussian kernel width can be tuned to application-specific requirements. Experimental results show that selectively using high-confidence predictions yields significantly improved localization accuracy, highlighting the practical benefits of integrating reliability into deep learning-based DOA estimation.

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。

↑