Joint Framework of Curriculum Learning and Knowledge Distillation for Noise-Robust and Small-Footprint Keyword Spotting-Reference-Cited by-同舟云学术

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

Published:2023 Issue: Volume:11 Page:100540-100553
ISSN:2169-3536
Container-title:IEEE Access
language:
Short-container-title:IEEE Access

Author:

Lim Jaebong¹^ORCID,Baek Yunju¹^ORCID

Affiliation:

1. School of Computer Science and Engineering, Pusan National University, Busan, South Korea

Funder

MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program

IIT

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

General Engineering,General Materials Science,General Computer Science,Electrical and Electronic Engineering

Link

http://xplorestaging.ieee.org/ielx7/6287639/10005208/10247011.pdf?arnumber=10247011

Reference44 articles.

1. An investigation of deep neural networks for noise robust speech recognition

2. Audio augmentation for speech recognition

3. Hotword Cleaner: Dual-microphone Adaptive Noise Cancellation with Deferred Filter Coefficients for Robust Keyword Spotting

4. Improving the robustness of DistilHuBERT to unseen noisy conditions via data augmentation, curriculum learning, and multi-task enhancement;guimaraes;Proc ENLSP-II NeurIPS Workshop,2022

5. A curriculum learning method for improved noise robustness in automatic speech recognition

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Optimizing Music Source Separation In Complex Audio Environments Through Progressive Self-Knowledge Distillation;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14