Long-Term Mask and Short-Term Correlation Learning Framework for Speaker Verification
Authors:
- Wenwen LiWLWenwen Li
- Chen ChenCCChen Chen
- Hailu YangHYHailu Yang
- Lili WangLWLili Wang
- 7 August 2026
- journal article
- Published by Springer Nature in Circuits, Systems, and Signal Processing
Abstract
No abstract availableFunding Information
- Science Fund for Distinguished Young Scholars of Heilongjiang Province (No.YQ2024F018)
- National Natural Science Foundation of China (No.62101163)
This publication has 34 references indexed in Scilit:
- Target Speaker Isolation for Mobile Health Assessment From Speech With CrosstalkIEEE Access, 2026
- Multidimensional acoustic feature fusion with attention-guided light weighted CNN for improved speaker recognitionEvolving Systems, 2026
- A lightweight meta-learning-based open-set speaker identification system with integrated spoofing and impostor detectionBiomedical Signal Processing and Control, 2025
- Robust Speaker Recognition for Whispered Speech2025
- Convolutional neural network-based detection of audio replay attacks in speaker verification systemsInternational Journal of Speech Technology, 2025
- Dimension-Specific Margins and Element-Wise Gradient Scaling for Enhanced Matryoshka Speaker EmbeddingIEEE Access, 2025
- A High-Performance Neural Network SoC for End-to-End Speaker VerificationIEEE Access, 2024
- Harnessing the power of Wav2Vec2 and CNNs for Robust Speaker Identification on the VoxCeleb and LibriSpeech DatasetsExpert Systems with Applications, 2024
- Resformer: Local Frame-Level Feature and Global Segment-Level Feature Joint Learning for Speaker VerificationCircuits, Systems, and Signal Processing, 2024
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition2019