Distilling Attention Knowledge for Speaker Verification
Zezhong Jin, Shujie Liu, Zhe Li, Chong-Xin Gan, Zilong Huang, Man‐Wai Mak, Kong Aik Lee
Hong Kong Polytechnic University Microsoft Research Asia (China) University of Hong Kong
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
In recent years, the adoption of pre-trained speech models as feature extractors for speaker verification (SV) has surged. To reduce model complexity, knowledge from these pre-trained models has been transferred to compact student models, enabling them to achieve performance unattainable by conventional methods. While label-level and feature-level knowledge distillation (KD) have both yielded promising results in SV, attention-level KD remains under explored. Different from the other two methods, attention-level KD aims to guide the student network to focus more on the informative and important parts of the feature. To explore the attention-level KD in SV tasks, in this paper, we develop two distinct attention maps that enable the student model to learn the teacher’s attention along both the frequency and temporal dimensions, named Frequency-attentive KD (FREQ-AKD) and Temporal-attentive KD (TEMPO-AKD), respectively. Experiments conducted on the VoxCeleb and CN-Celeb datasets demonstrate the effectiveness of both FREQ-AKD and TEMPO-AKD.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AISpeech Recognition and Synthesis
Speech and Audio Processing · Domain Adaptation and Few-Shot Learning