论文解读
Cross-Architecture Knowledge Distillation of WavLM for Lightweight Speaker Verification
说话人验证 | 8.0/10
说话人验证
论文解读
Cross-Domain Contrastive Learning with Dynamic Threshold Calibration for Source Speaker Tracing
说话人验证 | 8.0/10
论文解读
Curriculum Learning with Contrastive Loss for Lightweight Speaker Verification
说话人验证 | 6.5/10
论文解读
Distilling Attention Knowledge for Speaker Verification
说话人验证 | 8.0/10
论文解读
Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation Guided Structured Pruning
说话人验证 | 7.5/10
论文解读
Face-Voice Association with Inductive Bias for Maximum Class Separation
说话人验证 | 7.0/10
论文解读
Hybrid Pruning: In-Situ Compression of Self-Supervised Speech Models for Speaker Verification and Anti-Spoofing
说话人验证 | 8.0/10
会议任务专题
ICASSP 2026 - 说话人验证
共 10 篇 ICASSP 2026 说话人验证 方向论文
论文解读
Impact of Phonetics on Speaker Identity in Adversarial Voice Attack
说话人验证 | 7.0/10
论文解读
Linguard: Authenticating Speech Recordings Using Speech Recognition and Watermark
音频安全 | 6.5/10
论文解读
Target Speaker Anonymization in Multi-Speaker Recordings
语音匿名化 | 7.6/10
论文解读
Triage Knowledge Distillation for Speaker Verification
说话人验证 | 7.5/10
论文解读
UNet-Based Fusion and Exponential Moving Average Adaptation for Noise-Robust Speaker Recognition
说话人验证 | 7.5/10
论文解读
Enhancing Speaker Verification with Whispered Speech via Post-Processing
1. **问题**：耳语语音因缺乏声带振动，其声学特征与正常语音差异显著，导致现有的说话人验证系统性能严重下降。这在用户为保护隐私而低语、或因疾病无法正常发声等实际场景中构成挑战。 2. **方法核心**：在预训练的说话人验证骨干网络（ReDimNet-B6）之上，添加一个轻量级的编码器-解码器结构