Deep Speaker: an End-to-End Neural Speaker Embedding System
——arXiv 2017
一、论文主要贡献:
提出Deep Speaker系统(a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity.)
二、评估实验
(一)说明:
Deep Speaker: an End-to-End Neural Speaker Embedding System
(二)Deep Speaker总体框架
Deep Speaker: an End-to-End Neural Speaker Embedding System
(三)ResCNN模型框架
Deep Speaker: an End-to-End Neural Speaker Embedding SystemDeep Speaker: an End-to-End Neural Speaker Embedding System
(四)GRU模型框架
Deep Speaker: an End-to-End Neural Speaker Embedding SystemDeep Speaker: an End-to-End Neural Speaker Embedding System
(五)实验结果
Deep Speaker: an End-to-End Neural Speaker Embedding System
Deep Speaker: an End-to-End Neural Speaker Embedding System

三、复现代码(ing)
四、参考博客等资料
https://www.cnblogs.com/mengnan/p/10813745.html
https://www.sohu.com/a/139785058_465975
https://zhuanlan.zhihu.com/p/35687281

相关文章:

  • 2021-12-12
  • 2021-10-21
  • 2021-10-04
  • 2021-11-09
  • 2021-12-01
  • 2021-12-04
  • 2021-07-01
  • 2021-11-26
猜你喜欢
  • 2021-07-18
  • 2021-09-22
  • 2021-07-23
  • 2021-12-18
  • 2022-12-23
  • 2021-05-27
  • 2021-10-03
相关资源
相似解决方案