Joint Framework of Curriculum Learning and Knowledge Distillation for Noise-Robust and Small-Footprint Keyword Spotting

Joint Framework of Curriculum Learning and Knowledge Distillation for Noise-Robust and Small-Footprint Keyword Spotting

Spoken keyword spotting, which is characterized by simplicity and low latency, has been widely used in consumer electronics to facilitate always-on voice interfaces. Small-footprint keyword spotting based on tiny convolutional neural networks can be implemented on resource-constrained, yet energy-ef...

Cijeli opis

Bibliografski detalji
Glavni autori: Jaebong Lim, Yunju Baek
Format: Članak
Jezik:English
Izdano: IEEE 2023-01-01
Serija:IEEE Access
Teme:
Curriculum learning
data augmentation
joint framework
knowledge distillation
neural network compression
noise-robust keyword spotting
Online pristup:https://ieeexplore.ieee.org/document/10247011/

Internet

https://ieeexplore.ieee.org/document/10247011/

Slični predmeti