Speech Model Pre-training for End-to-End Spoken Language Understanding
TL
TL;DR
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 is proposed and improves performance both when the full dataset is used for training and when only a small subset is used.
Abstract
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.
References43 items
1
Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models
2
Interpretable Convolutional Filters with SincNet
3
A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
4
Spoken Language Understanding on the Edge
5