Towards Lifelong Learning of End-to-end ASR
This addresses the problem of performance degradation in ASR systems when faced with changing real-world conditions, representing an incremental step toward more adaptable technologies.
The paper tackles catastrophic forgetting in automatic speech recognition (ASR) when adapting to new environments, achieving a 28.7% relative reduction in word error rate compared to fine-tuning by applying lifelong learning methods to end-to-end ASR.
Automatic speech recognition (ASR) technologies today are primarily optimized for given datasets; thus, any changes in the application environment (e.g., acoustic conditions or topic domains) may inevitably degrade the performance. We can collect new data describing the new environment and fine-tune the system, but this naturally leads to higher error rates for the earlier datasets, referred to as catastrophic forgetting. The concept of lifelong learning (LLL) aiming to enable a machine to sequentially learn new tasks from new datasets describing the changing real world without forgetting the previously learned knowledge is thus brought to attention. This paper reports, to our knowledge, the first effort to extensively consider and analyze the use of various approaches of LLL in end-to-end (E2E) ASR, including proposing novel methods in saving data for past domains to mitigate the catastrophic forgetting problem. An overall relative reduction of 28.7% in WER was achieved compared to the fine-tuning baseline when sequentially learning on three very different benchmark corpora. This can be the first step toward the highly desired ASR technologies capable of synchronizing with the continuously changing real world.