arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.13268eess.AScs.SD
收藏

CEC:一种用于说话人识别的噪声标签检测方法

CEC: A Noisy Label Detection Method for Speaker Recognition

China Mobile Research Institute(中国移动研究院)

Yao Shen, Yingying Gao, Yaqian Hao, Chenguang Hu, Fulin Zhang, Junlan Feng, Shilei Zhang

AI总结:

针对说话人识别中的噪声标签问题,提出基于CIC、TIC指标的CEC检测方法,通过样本分类与渐进式难样本训练防过拟合,在说话人验证和噪声标签检测上均优于对比方案。

摘要:

噪声标签即使在标注精良的数据集中也不可避免,检测噪声标签对提升说话人识别模型的鲁棒性至关重要。本文提出一种基于两个全新统计指标的新型噪声标签检测方法:连续不一致计数(CIC)和总不一致计数(TIC),这两个指标通过跨轮次计数(CEC)计算,分别对应训练的早期和晚期阶段。此外,我们根据样本的预测结果将其分为三类:不一致样本、难样本和易样本。训练过程中,我们逐步提升难样本的难度来更新模型参数,防止噪声标签被过拟合。与对比方案相比,本文方法不仅在说话人验证任务上取得了最优性能,在噪声标签检测方面也表现出色。

英文摘要:

Noisy labels are inevitable, even in well-annotated datasets. The detection of noisy labels is of significant importance to enhance the robustness of speaker recognition models. In this paper, we propose a novel noisy label detection approach based on two new statistical metrics: Continuous Inconsistent Counting (CIC) and Total Inconsistent Counting (TIC). These metrics are calculated through Cross-Epoch Counting (CEC) and correspond to the early and late stages of training, respectively. Additionally, we categorize samples based on their prediction results into three categories: inconsistent samples, hard samples, and easy samples. During training, we gradually increase the difficulty of hard samples to update model parameters, preventing noisy labels from being overfitted. Compared to contrastive schemes, our approach not only achieves the best performance in speaker verification but also excels in noisy label detection.

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。

↑