Continual Learning For Monolingual End-to-end Automatic Speech Recognition

Abstract

Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF). Even monolingual ASR models cannot be extended to new accents, dialects, topics, etc. without suffering from CF, making them unable to be continually enhanced without storing all past data. Fortunately, Continual Learning (CL) methods, which aim to enable continual adaptation while overcoming CF, can be used. In this paper, we implement an extensive number of CL methods for End-to-End ASR and test and compare their ability to extend a monolingual Hybrid CTC-Transformer model across four new tasks. We find that the best performing CL method closes the gap between the fine-tuned model (lower bound) and the model trained jointly on all tasks (upper bound) by more than 40%, while requiring access to only 0.6% of the original data.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keyeeckt2021continual

Related papers

• Rehearsal-free Online Continual Learning For Automatic Speech Recognition (2023)5.24
• Unsupervised Online Continual Learning For Automatic Speech Recognition (2024)4.52
• Continual Learning Optimizations For Auto-regressive Decoder Of Multilingual ASR Systems (2024)5.84
• Multilingual Training And Cross-lingual Adaptation On Ctc-based Acoustic Model (2017)0.00
• Weight Averaging: A Simple Yet Effective Method To Overcome Catastrophic Forgetting In Automatic Speech Recognition (2022)6.34
• Updating Only Encoders Prevents Catastrophic Forgetting Of End-to-end ASR Models (2022)5.24
• Continuously Learning New Words In Automatic Speech Recognition (2024)0.00
• Multiple-hypothesis Ctc-based Semi-supervised Adaptation Of End-to-end Speech Recognition (2021)5.84