Multitask Training with Text Data for End-to-End Speech Recognition - (3 minutes introduction)

Title: Multitask Training with Text Data for End-to-End Speech Recognition - (3 minutes introduction)

Authors: Peidong Wang (Google, USA), Tara N. Sainath (Google, USA), Ron J. Weiss (Google, USA)

Category: Neural network training methods for ASR

Abstract: 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 960-hour 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.

d02s28t08trim

[elonmuskfan]

Can you share the code with me if you have done it in matlab?