Unsupervised Online Continual Learning for Automatic Speech Recognition

2024-06-18 · Steven Vander Eeckt, Hugo Van hamme

Adapting Automatic Speech Recognition (ASR) models to new domains leads to Catastrophic Forgetting (CF) of previously learned information. This paper addresses CF in the challenging context of Online Continual Learning (OCL), with tasks presented as a continuous data stream with unknown boundaries. We extend OCL for ASR into the unsupervised realm, by leveraging self-training (ST) to facilitate unsupervised adaptation, enabling models to adapt continually without label dependency and without forgetting previous knowledge. Through comparative analysis of various OCL and ST methods across two domain adaptation experiments, we show that UOCL suffers from significantly less forgetting compared to supervised OCL, allowing UOCL methods to approach the performance levels of supervised OCL. Our proposed UOCL extensions further boosts UOCL's efficacy. Our findings represent a significant step towards continually adaptable ASR systems, capable of leveraging unlabeled data across diverse domains.

📄 PDF Abstract BibTeX arXiv:2406.12503

Code (1)

stevenvdeeckt/unsupervised-ocl-for-asr 공식 구현

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Continual Learning Domain Adaptation speech-recognition Speech Recognition

Online Continual Learning of End-to-End Speech Recognition Models

2022-07-11 · Muqiao Yang, Ian Lane, Shinji Watanabe

Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptati…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Continual Learning Lifelong learning+3

Rehearsal-Free Online Continual Learning for Automatic Speech Recognition

2023-06-19 · Steven Vander Eeckt, Hugo Van hamme

Fine-tuning an Automatic Speech Recognition (ASR) model to new domains results in degradation on original domains, referred to as Catastrophic Forgetting (CF). Continual Learning (CL) attempts to train ASR models without…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Continual Learning speech-recognition+1

Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition

2023-07-14 · Theresa Pekarek Rosin, Stefan Wermter

While Automatic Speech Recognition (ASR) models have shown significant advances with the introduction of unsupervised or self-supervised training techniques, these improvements are still only limited to a subsection of l…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Continual Learning speech-recognition+2

Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech

2024-06-16 · Guan-Ting Lin, Wei-Ping Huang, Hung-Yi Lee

Deep Learning-based end-to-end Automatic Speech Recognition (ASR) has made significant strides but still struggles with performance on out-of-domain samples due to domain shifts in real-world scenarios. Test-Time Adaptat…

Automatic Speech Recognition Automatic Speech Recognition (ASR)speech-recognition Speech Recognition+1

Continual Learning in Machine Speech Chain Using Gradient Episodic Memory

2024-11-27 · Geoffrey Tyndall, Kurniawati Azizah, Dipta Tanaya, Ayu Purwarianti 외

Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introdu…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Continual Learning speech-recognition+3