Artificial intelligence

Physics

Meteorology

Spoken language

Training (meteorology)

Computer science

End-to-end principle

Language model

Natural language processing

Speech recognition

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-toend SLU systems map speech directly to intent through a single trainable model.Achieving high accuracy with these end-toend models without a large amount of training data is difficult.We propose a method to reduce the data requirements of endto-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.

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