太原理工大学学报2024，Vol.55Issue(4)：720-726,7.DOI:10.16355/j.tyut.1007-9432.20230259
基于多任务自适应知识蒸馏的语音增强
Speech Enhancement Based on Multi-Task Adaptive Knowledge Distillation
摘要
Abstract
[Purposes]In order to solve the computational cost problem of complex model in time and hardware,and improve the performance of speech enhancement algorithm,a speech en-hancement algorithm using multi-task adaptive knowledge distillation is proposed.[Methods]First,the idea of knowledge distillation is adopted to solve the problems that the existing speech enhancement model is too large,has many parameters,and has high calculation cost.Second,the differences between different time-frequency units are fully considered,and the weighting fac-tor is introduced to optimize the traditional loss function to improve the network performance of students.In order to avoid the uncertainty of teacher network prediction affecting the perform-ance of student network,the knowledge distillation network of multi-task adaptive learning is built to better utilize the correlation between different tasks to optimize the model.[Findings]The simulation results show that the proposed algorithm can effectively improve the performance of speech enhancement model while reducing the number of parameters and shortening the calcu-lation time.关键词
语音增强/知识 蒸馏/多任务自适应学习/加权损 失函数Key words
speech enhancement/knowledge distillation/multi-task adaptive learning/weigh-ted loss function分类
信息技术与安全科学引用本文复制引用
张刚敏,李雅荣,贾海蓉,王鲜霞,段淑斐..基于多任务自适应知识蒸馏的语音增强[J].太原理工大学学报,2024,55(4):720-726,7.基金项目
国家自然科学基金资助项目(12004275) （12004275）
Shanxi Scholarship Council of China(2020-042) （2020-042）
山西省自然科学基金资助项目(20210302123186) （20210302123186）
