Incremental Learning for End-to-End Automatic Speech Recognition
share
We propose an incremental learning for end-to-end Automatic Speech Recognition (ASR) to extend the model's capacity on a new task while retaining the performance on existing ones. The proposed method is effective without accessing to the old dataset to address the issues of high training cost and old dataset unavailability. To achieve this, knowledge distillation is applied as a guidance to retain the recognition ability from the previous model, which is then combined with the new ASR task for model optimization. With an ASR model pre-trained on 12,000h Mandarin speech, we test our proposed method on 300h new scenario task and 1h new named entities task. Experiments show that our method yields 3.25 on the new scenario, when compared with the pre-trained model and the full-data retraining baseline, respectively. It even yields a surprising 0.37 CER reduction on the new scenario than the fine-tuning. For the new named entities task, our method significantly improves the accuracy compared with the pre-trained model, i.e. 16.95 adaptions, the new models still maintain a same accuracy with the baseline on the old tasks.
READ FULL TEXT