# Dialogue history integration into end-to-end signal-to-concept spoken language understanding systems

arXiv: https://arxiv.org/abs/2002.06012 · HTML: https://mlsanity.com/paper/2002.06012/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2020.

## Built on by (most cited first, 10 of 10)

- [End2End Acoustic to Semantic Transduction](https://mlsanity.com/paper/2102.01013/) (2021)
- [Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding](https://mlsanity.com/paper/2102.06750/) (2021)
- [Integrating Dialog History into End-to-End Spoken Language Understanding Systems](https://mlsanity.com/paper/2108.08405/) (2021)
- [FANS: Fusing ASR and NLU for on-device SLU](https://mlsanity.com/paper/2111.00400/) (2021)
- [Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding](https://mlsanity.com/paper/2204.05169/) (2022)
- [Context-aware Fine-tuning of Self-supervised Speech Models](https://mlsanity.com/paper/2212.08542/) (2022)
- [OLISIA: a Cascade System for Spoken Dialogue State Tracking](https://mlsanity.com/paper/2304.11073/) (2023)
- [Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History](https://mlsanity.com/paper/2305.00926/) (2023)
- [Generative Context-aware Fine-tuning of Self-supervised Speech Models](https://mlsanity.com/paper/2312.09895/) (2023)
- [Is one brick enough to break the wall of spoken dialogue state tracking?](https://mlsanity.com/paper/2311.04923/) (2023)

## Abstract (arXiv)

This work investigates the embeddings for representing dialog history in spoken language understanding (SLU) systems. We focus on the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. We proposed to integrate dialogue history into an end-to-end signal-to-concept SLU system. The dialog history is represented in the form of dialog history embedding vectors (so-called h-vectors) and is provided as an additional information to end-to-end SLU models in order to improve the system performance. Three following types of h-vectors are proposed and experimentally evaluated in this paper: (1) supervised-all embeddings predicting bag-of-concepts expected in the answer of the user from the last dialog system response; (2) supervised-freq embeddings focusing on predicting only a selected set of semantic concept (corresponding to the most frequent errors in our experiments); and (3) unsupervised embeddings. Experiments on the MEDIA corpus for the semantic slot filling task demonstrate that the proposed h-vectors improve the model performance.