# Cross-utterance ASR Rescoring with Graph-based Label Propagation

arXiv: https://arxiv.org/abs/2303.15132 · HTML: https://mlsanity.com/paper/2303.15132/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 13 of 13)

- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Fairness in Recommendation Ranking through Pairwise Comparisons](https://mlsanity.com/paper/1903.00780/) (2019)
- [Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/1908.10992/) (2019)
- [Deep Metric Transfer for Label Propagation with Limited Annotated Data](https://mlsanity.com/paper/1812.08781/) (2018)
- [Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities](https://mlsanity.com/paper/2207.11345/) (2022)
- [Audio-attention discriminative language model for ASR rescoring](https://mlsanity.com/paper/1912.03363/) (2019)
- [Deep Graph Random Process for Relational-Thinking-Based Speech Recognition](https://mlsanity.com/paper/2007.02126/) (2020)
- [Improving fairness in speaker verification via Group-adapted Fusion Network](https://mlsanity.com/paper/2202.11323/) (2022)
- [Cross-utterance Reranking Models with BERT and Graph Convolutional Networks for Conversational Speech Recognition](https://mlsanity.com/paper/2106.06922/) (2021)
- [Graph-based Label Propagation for Semi-Supervised Speaker Identification](https://mlsanity.com/paper/2106.08207/) (2021)
- [Graph-based Multi-View Fusion and Local Adaptation: Mitigating Within-Household Confusability for Speaker Identification](https://mlsanity.com/paper/2207.04081/) (2022)

## Built on by (most cited first, 1 of 1)

- [Learning from Limited Labels: Transductive Graph Label Propagation for Indian Music Analysis](https://mlsanity.com/paper/2601.03626/) (2026)

## Abstract (arXiv)

We propose a novel approach for ASR N-best hypothesis rescoring with graph-based label propagation by leveraging cross-utterance acoustic similarity. In contrast to conventional neural language model (LM) based ASR rescoring/reranking models, our approach focuses on acoustic information and conducts the rescoring collaboratively among utterances, instead of individually. Experiments on the VCTK dataset demonstrate that our approach consistently improves ASR performance, as well as fairness across speaker groups with different accents. Our approach provides a low-cost solution for mitigating the majoritarian bias of ASR systems, without the need to train new domain- or accent-specific models.