# Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data

arXiv: https://arxiv.org/abs/2307.01764 · HTML: https://mlsanity.com/paper/2307.01764/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 4 Jul 2023.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [BERT for Joint Intent Classification and Slot Filling](https://mlsanity.com/paper/1902.10909/) (2019)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1907.05774/) (2019)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network](https://mlsanity.com/paper/2006.05702/) (2020)
- [A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding](https://mlsanity.com/paper/2111.02735/) (2021)
- [Deep Shallow Fusion for RNN-T Personalization](https://mlsanity.com/paper/2011.07754/) (2020)
- [Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking](https://mlsanity.com/paper/2105.04222/) (2021)
- [ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet](https://mlsanity.com/paper/2111.14706/) (2021)
- [Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations](https://mlsanity.com/paper/2005.08866/) (2020)
- [Class LM and word mapping for contextual biasing in End-to-End ASR](https://mlsanity.com/paper/2007.05609/) (2020)
- [Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2008.06239/) (2020)
- [Robust Zero-Shot Cross-Domain Slot Filling with Example Values](https://mlsanity.com/paper/1906.06870/) (2019)
- [Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling](https://mlsanity.com/paper/2004.11727/) (2020)
- [Multilingual and Cross-Lingual Intent Detection from Spoken Data](https://mlsanity.com/paper/2104.08524/) (2021)
- [Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition](https://mlsanity.com/paper/2109.00627/) (2021)
- [Joint Contextual Modeling for ASR Correction and Language Understanding](https://mlsanity.com/paper/2002.00750/) (2020)
- [Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition](https://mlsanity.com/paper/2107.02268/) (2021)
- [Language Model is All You Need: Natural Language Understanding as Question Answering](https://mlsanity.com/paper/2011.03023/) (2020)
- [An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking](https://mlsanity.com/paper/1805.01555/) (2018)
- [End-to-end contextual speech recognition using class language models and a token passing decoder](https://mlsanity.com/paper/1812.02142/) (2018)
- [ConVEx: Data-Efficient and Few-Shot Slot Labeling](https://mlsanity.com/paper/2010.11791/) (2020)

## Built on by (most cited first, 3 of 3)

- [Bayesian WeakS-to-Strong from Text Classification to Generation](https://mlsanity.com/paper/2406.03199/) (2024)
- [Speech-based Slot Filling using Large Language Models](https://mlsanity.com/paper/2311.07418/) (2023)
- [AVERT: Audio-Verified Adjudication for Spoken Dialogue State Tracking](https://mlsanity.com/paper/2609.01828/) (2026)

## Abstract (arXiv)

Manually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling methods that operate with limited amounts of labelled data. Moreover, the majority of current work on ToD is based solely on text as the input modality, neglecting the additional challenges of imperfect automatic speech recognition (ASR) when working with spoken language. In this work, we propose a Knowledge-Aware Audio-Grounded generative slot-filling framework, termed KA2G, that focuses on few-shot and zero-shot slot filling for ToD with speech input. KA2G achieves robust and data-efficient slot filling for speech-based ToD by 1) framing it as a text generation task, 2) grounding text generation additionally in the audio modality, and 3) conditioning on available external knowledge (e.g. a predefined list of possible slot values). We show that combining both modalities within the KA2G framework improves the robustness against ASR errors. Further, the knowledge-aware slot-value generator in KA2G, implemented via a pointer generator mechanism, particularly benefits few-shot and zero-shot learning. Experiments, conducted on the standard speech-based single-turn SLURP dataset and a multi-turn dataset extracted from a commercial ToD system, display strong and consistent gains over prior work, especially in few-shot and zero-shot setups.