App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 12

Self-bootstrapping cross-modal voice-face matching method via pseudo-label confidence weighting

Sun Xiang
Zeng Zhaolong
Bu Fanliang
Ma Qiming
Peoples Public Security University of China, Beijing 100038, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0101

Abstract

This work addresses the challenges of large modality heterogeneity, noisy pseudo-labels, and improper negative sample selection in voice-face cross-modal matching, aiming to build a robust identity authentication system with enhanced association accuracy and stability. We propose a self-bootstrapping cross-modal voice-face matching method via pseudo-label confidence weighting. Built upon the Self-Lifting framework, we design a learnable confidence weighting mechanism that employs a compact confidence prediction network to dynamically estimate sample uncertainty in the embedding space, and applies weighting during both sampling and loss computation to suppress noise. We introduce a multi-level loss function that combines confidence-weighted Multi-Similarity Loss, bidirectional cross-modal contrastive loss, and MSE loss, jointly promoting intra-modal discriminability and cross-modal alignment. We optimize the clustering strategy with dynamic frequency modulation and warm-start initialization to improve efficiency and stability. In cross-modal verification, our method achieves an AUC of 87.8% under the ungendered protocol and 76.6% under the gendered protocol. The 1: 2 matching accuracy reaches 86.6% in the V-F direction and 87.0% in the F-V direction. In 1: N matching and retrieval tasks, the framework substantially outperforms state-of-the-art methods. Ablation studies confirm the effectiveness of each component. The proposed approach effectively mitigates pseudo-label noise and computational overhead, demonstrating superior robustness and generalization in demanding scenarios, and provides a reliable technical solution for cross-modal identity authentication.

Foundation Support

国家重点研发计划课题(2024YFC3306901)
基于"区块链+隐私计算"的数据融合分析技术研究资助项目(H20250013)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0101
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 12

Publish History

[2026-08-12] Accepted Paper

Cite This Article

孙翔, 曾昭龙, 卜凡亮, 等. 基于伪标签置信度加权的自举式跨模态语音-人脸匹配方法 [J]. 计算机应用研究, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0101. (Sun Xiang, Zeng Zhaolong, Bu Fanliang, et al. Self-bootstrapping cross-modal voice-face matching method via pseudo-label confidence weighting [J]. Application Research of Computers, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0101. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)