# On Building Spoken Language Understanding Systems for Low Resourced Languages

arXiv: https://arxiv.org/abs/2205.12818 · HTML: https://mlsanity.com/paper/2205.12818/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 25 May 2022.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog](https://mlsanity.com/paper/1810.13327/) (2018)
- [Towards end-to-end spoken language understanding](https://mlsanity.com/paper/1802.08395/) (2018)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [Spoken Language Understanding on the Edge](https://mlsanity.com/paper/1810.12735/) (2018)
- [HarperValleyBank: A Domain-Specific Spoken Dialog Corpus](https://mlsanity.com/paper/2010.13929/) (2020)
- [Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages](https://mlsanity.com/paper/2011.03646/) (2020)
- [Mere account mein kitna balance hai? -- On building voice enabled Banking Services for Multilingual Communities](https://mlsanity.com/paper/2010.16411/) (2020)
- [Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems](https://mlsanity.com/paper/2104.01287/) (2021)
- [Word-Free Spoken Language Understanding for Mandarin-Chinese](https://mlsanity.com/paper/2107.00186/) (2021)

## Built on by (most cited first, 4 of 4)

- [Textually Pretrained Speech Language Models](https://mlsanity.com/paper/2305.13009/) (2023)
- [Decoding Emotions: A comprehensive Multilingual Study of Speech Models for Speech Emotion Recognition](https://mlsanity.com/paper/2308.08713/) (2023)
- [Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages](https://mlsanity.com/paper/2404.18286/) (2024)
- [Creating Spoken Dialog Systems in Ultra-Low Resourced Settings](https://mlsanity.com/paper/2312.06266/) (2023)

## Abstract (arXiv)

Spoken dialog systems are slowly becoming and integral part of the human experience due to their various advantages over textual interfaces. Spoken language understanding (SLU) systems are fundamental building blocks of spoken dialog systems. But creating SLU systems for low resourced languages is still a challenge. In a large number of low resourced language, we don't have access to enough data to build automatic speech recognition (ASR) technologies, which are fundamental to any SLU system. Also, ASR based SLU systems do not generalize to unwritten languages. In this paper, we present a series of experiments to explore extremely low-resourced settings where we perform intent classification with systems trained on as low as one data-point per intent and with only one speaker in the dataset. We also work in a low-resourced setting where we do not use language specific ASR systems to transcribe input speech, which compounds the challenge of building SLU systems to simulate a true low-resourced setting. We test our system on Belgian Dutch (Flemish) and English and find that using phonetic transcriptions to make intent classification systems in such low-resourced setting performs significantly better than using speech features. Specifically, when using a phonetic transcription based system over a feature based system, we see average improvements of 12.37% and 13.08% for binary and four-class classification problems respectively, when averaged over 49 different experimental settings.