CEC: A Noisy Label Detection Method for Speaker Recognition
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments
From Dialect Gaps to Identity Maps: Tackling Variability in Speaker Verification
Investigation of Speaker Representation for Target-Speaker Speech Processing
Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels
토론
이 논문과 연결된 포럼 글이 아직 없습니다.