# Deep Graph Random Process for Relational-Thinking-Based Speech Recognition

arXiv: https://arxiv.org/abs/2007.02126 · HTML: https://mlsanity.com/paper/2007.02126/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [Temporal Sentence Grounding in Videos: A Survey and Future Directions](https://mlsanity.com/paper/2201.08071/) (2022)
- [OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks](https://mlsanity.com/paper/2203.15209/) (2022)
- [Taxonomy-Structured Domain Adaptation](https://mlsanity.com/paper/2306.07874/) (2023)
- [STRODE: Stochastic Boundary Ordinary Differential Equation](https://mlsanity.com/paper/2107.08273/) (2021)
- [Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset](https://mlsanity.com/paper/2402.05547/) (2024)
- [Cross-utterance ASR Rescoring with Graph-based Label Propagation](https://mlsanity.com/paper/2303.15132/) (2023)
- [Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling](https://mlsanity.com/paper/2309.11983/) (2023)
- [LERD: Latent Event-Relational Dynamics for Neurodegenerative Classification](https://mlsanity.com/paper/2602.18195/) (2026)
- [Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization](https://mlsanity.com/paper/2205.02670/) (2022)
- [Multi-party Response Generation with Relation Disentanglement](https://mlsanity.com/paper/2403.10827/) (2024)
- [A Joint Spectro-Temporal Relational Thinking Based Acoustic Modeling Framework](https://mlsanity.com/paper/2409.15357/) (2024)
- [iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis](https://mlsanity.com/paper/2605.30179/) (2026)

## Abstract (arXiv)

Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a recognizable concept or object through coupling and transformation of these percepts. Such mental processes are difficult to model in real-world problems such as in conversational automatic speech recognition (ASR), as the percepts (if they are modelled as graphs indicating relationships among utterances) are supposed to be innumerable and not directly observable. In this paper, we present a Bayesian nonparametric deep learning method called deep graph random process (DGP) that can generate an infinite number of probabilistic graphs representing percepts. We further provide a closed-form solution for coupling and transformation of these percept graphs for acoustic modeling. Our approach is able to successfully infer relations among utterances without using any relational data during training. Experimental evaluations on ASR tasks including CHiME-2 and CHiME-5 demonstrate the effectiveness and benefits of our method.