# Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking

arXiv: https://arxiv.org/abs/1707.05853 · HTML: https://mlsanity.com/paper/1707.05853/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2017.

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

- [N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses](https://mlsanity.com/paper/2106.06519/) (2021)
- [Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation](https://mlsanity.com/paper/2110.10261/) (2021)

## Abstract (arXiv)

This paper presents our novel method to encode word confusion networks, which can represent a rich hypothesis space of automatic speech recognition systems, via recurrent neural networks. We demonstrate the utility of our approach for the task of dialog state tracking in spoken dialog systems that relies on automatic speech recognition output. Encoding confusion networks outperforms encoding the best hypothesis of the automatic speech recognition in a neural system for dialog state tracking on the well-known second Dialog State Tracking Challenge dataset.