event

Ph.D. Proposal Oral Exam - You Wang

Primary tabs

Title:  Attention-based Convolutional Neural Network Model and Its Combination with Few-shot Learning for Audio Classification

Committee: 

Dr. Anderson, Advisor

Dr. Rozell, Chair

Dr. Davenport

Abstract: The objective of the proposed research is to improve the performance of environmental sound and acoustic scene classification using an attention mechanism combined with few-shot learning to deal with data scarcity. The proposed work seeks to extract salient feature regions by introducing a new light-weight attention-based CNN model and combine it with few-shot learning approaches, especially prototypical networks to overcome the limitation of training data.

Status

  • Workflow Status:Published
  • Created By:Daniela Staiculescu
  • Created:12/08/2020
  • Modified By:Daniela Staiculescu
  • Modified:12/08/2020

Categories

Target Audience