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

arXiv: https://arxiv.org/abs/2103.16674 · HTML: https://mlsanity.com/paper/2103.16674/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [ERNIE 2.0: A Continual Pre-training Framework for Language Understanding](https://mlsanity.com/paper/1907.12412/) (2019)
- [Towards end-to-end spoken language understanding](https://mlsanity.com/paper/1802.08395/) (2018)
- [Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM](https://mlsanity.com/paper/1706.02737/) (2017)
- [Capsule Networks for Low Resource Spoken Language Understanding](https://mlsanity.com/paper/1805.02922/) (2018)
- [Multitask Learning with Capsule Networks for Speech-to-Intent Applications](https://mlsanity.com/paper/2002.07450/) (2020)
- [Improving Recurrent Neural Networks For Sequence Labelling](https://mlsanity.com/paper/1606.02555/) (2016)

## Built on by (most cited first, 2 of 2)

- [ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet](https://mlsanity.com/paper/2111.14706/) (2021)
- [Bidirectional Representations for Low Resource Spoken Language Understanding](https://mlsanity.com/paper/2211.14320/) (2022)

## Abstract (arXiv)

Designing a speech-to-intent (S2I) agent which maps the users' spoken commands to the agents' desired task actions can be challenging due to the diverse grammatical and lexical preference of different users. As a remedy, we discuss a user-taught S2I system in this paper. The user-taught system learns from scratch from the users' spoken input with action demonstration, which ensure it is fully matched to the users' way of formulating intents and their articulation habits. The main issue is the scarce training data due to the user effort involved. Existing state-of-art approaches in this setting are based on non-negative matrix factorization (NMF) and capsule networks. In this paper we combine the encoder of an end-to-end ASR system with the prior NMF/capsule network-based user-taught decoder, and investigate whether pre-training methodology can reduce training data requirements for the NMF and capsule network. Experimental results show the pre-trained ASR-NMF framework significantly outperforms other models, and also, we discuss limitations of pre-training with different types of command-and-control(C&C) applications.