Speech Model Pre-training for End-to-End Spoken Language Understanding

04/07/2019 ∙ by Loren Lugosch, et al. ∙ 0

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these end-to-end models without a large amount of training data is difficult. We propose a method to reduce the data requirements of end-to-end SLU in which the model is first pre-trained to predict words and phonemes, thus learning good features for SLU. We introduce a new SLU dataset, Fluent Speech Commands, and show that our method improves performance both when the full dataset is used for training and when only a small subset is used. We also describe preliminary experiments to gauge the model's ability to generalize to new phrases not heard during training.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

Code Repositories

pretrain_speech_model

Speech Model Pre-training for End-to-End Spoken Language Understanding


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.