Multitask Training with Text Data for End-to-End Speech Recognition

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.

References in corpus (5)

• Attention-Based Models for Speech Recognition
• Sequence Transduction with Recurrent Neural Networks
• Conformer: Convolution-augmented Transformer for Speech Recognition
• vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
• Almost Unsupervised Text to Speech and Automatic Speech Recognition

Cited by in corpus (1)

• Efficient End-to-End Speech Recognition Using Performers in Conformers