arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.20165cs.SDeess.AS
收藏

频谱或空间?在具有挑战性的数据条件下利用两者进行说话人提取

Spectral or spatial? Leveraging both for speaker extraction in challenging data conditions

Faculty of Engineering, Bar-Ilan University(巴伊兰大学工程学院);OriginAI

Aviad Eisenberg, Sharon Gannot, Shlomo E. Chazan

AI总结:

本文提出了一种结合频谱和空间信息的多通道说话人提取算法,通过动态平衡两种线索以提高在嘈杂和不准确数据下的鲁棒性。

摘要:

本文提出了一种稳健的多通道说话人提取算法,旨在处理参考信息中的不准确性。虽然现有方法往往仅依赖空间或频谱线索来识别目标说话人,我们的方法整合了两种信息源以提高鲁棒性。我们方法的一个关键方面是其强调稳定性,确保即使其中一个特征退化或误导时也能保持可靠的性能。给定一个嘈杂的混合信号和两个可能不可靠的线索,专门训练的网络被用来动态平衡它们的贡献或在必要时忽略信息较少的线索。我们通过使用简单的到达方向(DOA)估计器和嘈杂的频谱注册过程来模拟推理时间的误差,从而在具有挑战性的条件下评估该系统。实验结果表明,所提出的模型即使在存在大量参考不准确性的情况下也能成功提取所需说话人。

英文摘要:

This paper presents a robust multi-channel speaker extraction algorithm designed to handle inaccuracies in reference information. While existing approaches often rely solely on either spatial or spectral cues to identify the target speaker, our method integrates both sources of information to enhance robustness. A key aspect of our approach is its emphasis on stability, ensuring reliable performance even when one of the features is degraded or misleading. Given a noisy mixture and two potentially unreliable cues, a dedicated network is trained to dynamically balance their contributions-or disregard the less informative one when necessary. We evaluate the system under challenging conditions by simulating inference-time errors using a simple direction of arrival (DOA) estimator and a noisy spectral enrollment process. Experimental results demonstrate that the proposed model successfully extracts the desired speaker even in the presence of substantial reference inaccuracies.

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。

↑