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

• Published in: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5575 - 5579
• Main Authors: Sicheng Wang, Kehuang Li, Zhen Huang, Siniscalchi, Sabato Marco, Chin-Hui Lee
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2017
• Subjects: Knowledge engineering; model compression; model stacking; multi-task training; Neural networks; Noise measurement; Speech; Speech enhancement; Stacking; Training; Transfer learning
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP.2017.7953223

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, the knowledge embedded in the form of the output values of a high-performance DNN is used to guide the training of a smaller DNN model in sequential transfer learning. In the second multi-task transfer learning solution, the smaller DNN is trained to learn the output value of the larger DNN, and the speech enhancement task in parallel. Finally, a progressive stacking transfer learning is accomplished through multi-task learning, and DNN stacking. Our experimental evidences demonstrate 5 times parameter reduction while maintaining similar enhancement performance with the proposed framework.