DeepAI AI Chat
Log In Sign Up

Improving End-to-End Speech-to-Intent Classification with Reptile

by   Yusheng Tian, et al.
HUAWEI Technologies Co., Ltd.

End-to-end spoken language understanding (SLU) systems have many advantages over conventional pipeline systems, but collecting in-domain speech data to train an end-to-end system is costly and time consuming. One question arises from this: how to train an end-to-end SLU with limited amounts of data? Many researchers have explored approaches that make use of other related data resources, typically by pre-training parts of the model on high-resource speech recognition. In this paper, we suggest improving the generalization performance of SLU models with a non-standard learning algorithm, Reptile. Though Reptile was originally proposed for model-agnostic meta learning, we argue that it can also be used to directly learn a target task and result in better generalization than conventional gradient descent. In this work, we employ Reptile to the task of end-to-end spoken intent classification. Experiments on four datasets of different languages and domains show improvement of intent prediction accuracy, both when Reptile is used alone and used in addition to pre-training.


page 1

page 2

page 3

page 4


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

Whereas conventional spoken language understanding (SLU) systems map spe...

A Study of Different Ways to Use The Conformer Model For Spoken Language Understanding

SLU combines ASR and NLU capabilities to accomplish speech-to-intent und...

Improving the Intent Classification accuracy in Noisy Environment

Intent classification is a fundamental task in the spoken language under...

Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU

Intent classification is a major task in spoken language understanding (...

Pre-training for low resource speech-to-intent applications

Designing a speech-to-intent (S2I) agent which maps the users' spoken co...

Deep F-measure Maximization for End-to-End Speech Understanding

Spoken language understanding (SLU) datasets, like many other machine le...