Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition-Reference-Cited by-同舟云学术

Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Eeckt Steven Vander¹,Van Hamme Hugo¹

Affiliation:

1. KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium

Publisher

IEEE

Link

Reference31 articles.

3. Continual-wav2vec2: an application of continual learning for self-supervised automatic speech recognition;kessler;ICML,2021

4. Continual learning for monolingual end-to-end automatic speech recognition;eeckt;Proceedings EUSIPCO 2022,2022

5. Learning without forgetting;li;Computer Vision – ECCV 2016,0

Cited by 5 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. Task Vector Algebra for ASR Models;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. Exploring Adapters with Conformers for Children’s Automatic Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Unsupervised Accent Adaptation Through Masked Language Model Correction of Discrete Self-Supervised Speech Units;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Parameter-Efficient Tuning with Adaptive Bottlenecks for Automatic Speech Recognition;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16