Multi-Objective Progressive Clustering for Semi-Supervised Domain Adaptation in Speaker Verification

Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks. In this paper, we propose a novel pseudo-labeling method named Multi-objective Progressive Clustering (MoPC), specifically designed for semi-su...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 12236 - 12240
Hlavní autoři: Li, Ze, Lin, Yuke, Jiang, Ning, Qin, Xiaoyi, Zhao, Guoqing, Wu, Haiying, Li, Ming
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 14.04.2024
Témata:
Acoustics
Clustering algorithms
Domain Adaptation
Noise reduction
Semi-supervised
Signal processing
Signal processing algorithms
Speaker Recognition
Speech recognition
Target tracking
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks. In this paper, we propose a novel pseudo-labeling method named Multi-objective Progressive Clustering (MoPC), specifically designed for semi-supervised domain adaptation. Firstly, we utilize limited labeled data from the target domain to derive domain-specific descriptors based on multiple distinct objectives, namely within-graph denoising, intra-class denoising and inter-class denoising. Then, the Infomap algorithm is adopted for embedding clustering, and the descriptors are leveraged to further refine the target domain's pseudo-labels. Moreover, to further improve the quality of pseudo labels, we introduce the subcenter-purification and progressive-merging strategy for label denoising. Our proposed MoPC method achieves 4.95% EER and ranked the 1 st place on the evaluation set of VoxSRC 2023 track 3. We also conduct additional experiments on the FFSVC dataset and yield promising results.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10447138