Sequential Editing for Lifelong Training of Speech Recognition Models
This addresses computational inefficiencies for speech recognition systems needing to adapt to new domains, though it appears incremental as it builds on lifelong learning techniques.
The paper tackles the problem of catastrophic forgetting in automatic speech recognition when adding new domains, proposing sequential model editing as a method that achieves up to 15% word error rate reduction over fine-tuning without needing prior data or extra parameters.
Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on new domain risks Catastrophic Forgetting (CF). To address this, Lifelong Learning (LLL) algorithms have been proposed for ASR. Prior research has explored techniques such as Elastic Weight Consolidation, Knowledge Distillation, and Replay, all of which necessitate either additional parameters or access to prior domain data. We propose Sequential Model Editing as a novel method to continually learn new domains in ASR systems. Different than previous methods, our approach does not necessitate access to prior datasets or the introduction of extra parameters. Our study demonstrates up to 15% Word Error Rate Reduction (WERR) over fine-tuning baseline, and superior efficiency over other LLL techniques on CommonVoice English multi-accent dataset.