CEC: A Noisy Label Detection Method for Speaker Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Yao, Gao, Yingying, Hao, Yaqian, Hu, Chenguang, Zhang, Fulin, Feng, Junlan, Zhang, Shilei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917699396829184
author Shen, Yao
Gao, Yingying
Hao, Yaqian
Hu, Chenguang
Zhang, Fulin
Feng, Junlan
Zhang, Shilei
author_facet Shen, Yao
Gao, Yingying
Hao, Yaqian
Hu, Chenguang
Zhang, Fulin
Feng, Junlan
Zhang, Shilei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13268
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CEC: A Noisy Label Detection Method for Speaker Recognition
Shen, Yao
Gao, Yingying
Hao, Yaqian
Hu, Chenguang
Zhang, Fulin
Feng, Junlan
Zhang, Shilei
Audio and Speech Processing
Sound
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.
title CEC: A Noisy Label Detection Method for Speaker Recognition
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2406.13268