Knowledge Distillation in Acoustic Scene Classification

Knowledge Distillation in Acoustic Scene Classification

Common acoustic properties that different classes share degrades the performance of acoustic scene classification systems. This results in a phenomenon where a few confusing pairs of acoustic scenes dominate a significant proportion of all misclassified audio segments. In this article, we propose ad...

Full description

Bibliographic Details
Main Authors: Jee-Weon Jung, Hee-Soo Heo, Hye-Jin Shim, Ha-Jin Yu
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Acoustic scene classification
common properties among different acoustic scenes
deep neural networks
frequently misclassified pair
knowledge distillation
specialist models
Online Access:https://ieeexplore.ieee.org/document/9186616/

Internet

https://ieeexplore.ieee.org/document/9186616/

Similar Items