Compressing speaker extraction model with ultra-low precision quantization and knowledge distillation

作者：Yating Huang, Yunzhe Hao, Jiaming Xu, Bo Xu · 发表于：Neural Networks · 年份：2022 · DOI：10.1016/j.neunet.2022.06.026 · 被引用次数：18 · 研究领域：Speech and Audio Processing、Speech Recognition and Synthesis、Music and Audio Processing