Multitask Training with Text Data for End-to-End Speech Recognition
Peidong Wang, Tara N. Sainath, Ron J. Weiss · 2021
We propose a multitask training method for attention-based end-to-end speech recognition models.We regularize the decoder in a listen, attend, and spell model by multitask training it on both audio-text and text-only data.Trained on the 100-hour subset of LibriSpeech, the proposed method, without requiring an additional language model, leads to an 11% relative performance improvement over the baseline and approaches the performance of language model shallow fusion on the test-clean evaluation set.We observe a similar trend on the whole 960hour LibriSpeech training set.Analyses of different types of errors and sample output sentences demonstrate that the proposed method can incorporate language level information, suggesting its effectiveness in real-world applications.