← Search

Kehuang Li

2 accepted papers

2017

A transfer learning and progressive stacking approach to reducing deep model sizes with an application to speech enhancement

ICASSP 2017accepted

Leveraging upon transfer learning, we distill the knowledge in a conventional wide and deep neural network (DNN) into a narrower yet deeper model with fewer parameters and comparable system performance for speech enhancement. We present three transfer-learning solutions to accomplish our goal. First…

Cited by 0SourceScholar