Employing AI for Better Access to Justice: An Automatic Text-to-Video Linking Tool for UK Supreme Court Hearings
Source abstract
Abstract
The increasing adoption of artificial intelligence across domains presents new opportunities to enhance access to justice. In this paper, we introduce a human-centric AI tool that utilises advances in Automatic Speech Recognition (ASR) and Large Language Models (LLMs) to facilitate semantic linking between written UK Supreme Court (SC) judgements and their corresponding hearing videos. The motivation stems from the critical role UK SC hearings play in shaping landmark legal decisions, which often span several hours and remain difficult to navigate manually. Our approach involves two key components: (1) a customised ASR system fine-tuned on 139 h of manually edited SC hearing transcripts and legal documents and (2) a semantic linking module powered by GPT-based text embeddings adapted to the legal domain. The ASR system addresses domain-specific transcription challenges by incorporating a custom language model and legal phrase extraction techniques. The semantic linking module uses fine-tuned embeddings to match judgement paragraphs with relevant spans in the hearing transcripts. Quantitative evaluation shows that our customised ASR system improves transcription accuracy by 9% compared to generic ASR baselines. Furthermore, our adapted GPT embeddings achieve an F1 score of 0.85 in classifying relevant links between judgement text and hearing transcript segments. These results demonstrate the effectiveness of our system in streamlining access to critical legal information and supporting legal professionals in interpreting complex judicial decisions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Artificial Intelligence in Law · Legal Education and Practice Innovations · Comparative and International Law Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computing, Birminghan City University, Belmont Row, Birmingham B4 7RQ, UK
Centre for Translation Studies, University of Surrey, Guildford, Surrey GU2 7XH, UK
Kingfisher Labs Ltd., Cambridge, UK
Just Access, Leeds LS1 2BH, UK
Funding
Innovate UK project
References (56)
Show source-provided references
1. UK Supreme Court (2025, July 30). Annual Report and Accounts 2024–25. Available online: https://supremecourt.uk/uploads/The_Supreme_Court_Annual_Report_and_Accounts_2024_25_ec4ecbe2e5.pdf.
2. Saadany, H., Breslin, C., Orăsan, C., and Walker, S. (2023, January 19). Better Transcription of UK Supreme Court Hearings. Proceedings of the Workshop on Artificial Intelligence for Access to Justice (AI4AJ 2023), Braga, Portugal.
3. Saadany, H., and Orǎsan, C. (, January 6–10). Automatic Linking of Judgements to UK Supreme Court Hearings. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, Singapore.10.18653/v1/2023.emnlp-industry.47 ↗
4. Saadany, H., Orasan, C., Walker, S., and Breslin, C. (2024, January 20–25). Linking Judgement Text to Court Hearing Videos: UK Supreme Court as a Case Study. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Torino, Italy.
5. Elwany, E., Moore, D., and Oberoi, G. (2019). Bert goes to law school: Quantifying the competitive advantage of access to large legal corpora in contract understanding. arXiv.
6. Nay, J.J. (2021). Natural Language Processing for Legal Texts. Legal Informatics, Cambridge University Press.10.1017/9781316529683.011 ↗
7. Natural language processing in law: Prediction of outcomes in the higher courts of Turkey10.1016/j.ipm.2021.102684 ↗
8. Engstrom, D. (2022). Natural Language Processing in Legal Tech. Legal Tech and the Future of Civil Justice, Cambridge University Press.10.1017/9781009255301 ↗
9. Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., and Sutskever, I. (2023, January 23–29). Robust Speech Recognition via Large-Scale Weak Supervision. Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA.
10. Watanabe, S., Mandel, M., Barker, J., Vincent, E., Arora, A., Chang, X., Khudanpur, S., Manohar, V., Povey, D., and Raj, D. (2020, January 4). CHiME-6 Challenge: Tackling multispeaker speech recognition for unsegmented recordings. Proceedings of the CHiME 2020-6th International Workshop on Speech Processing in Everyday Environments, Online.10.21437/CHiME.2020-1 ↗
11. Feng, S., Kudina, O., Halpern, B.M., and Scharenborg, O. (2021). Quantifying bias in Automatic Speech Recognition. arXiv.
12. Zhang, Y. (2022, January 18–22). Mitigating bias against non-native accents. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Incheon, Republic of Korea.10.21437/Interspeech.2022-836 ↗
13. Mai, L., and Carson-Berndsen, J. (2022, January 18–22). Unsupervised domain adaptation for speech recognition with unsupervised error correction. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Incheon, Republic of Korea.10.21437/Interspeech.2022-10565 ↗
14. Huo, Z., Hwang, D., Sim, K.C., Garg, S., Misra, A., Siddhartha, N., Strohman, T., and Beaufays, F. (2021). Incremental layer-wise self-supervised learning for efficient speech domain adaptation on device. arXiv.10.21437/Interspeech.2022-10904 ↗
15. Sato, H., Komori, T., Mishima, T., Kawai, Y., Mochizuki, T., Sato, S., and Ogawa, T. (2022, January 18–22). Text-Only Domain Adaptation Based on Intermediate CTC. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Incheon, Republic of Korea.10.21437/Interspeech.2022-10114 ↗
16. Dingliwa, S., Shenoy, A., Bodapati, S., Gandhe, A., Gadde, R.T., and Kirchhoff, K. (2022, January 18–22). Domain prompts: Towards memory and compute efficient domain adaptation of ASR systems. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Incheon, Republic of Korea.10.21437/Interspeech.2022-824 ↗
17. Mani, A., Palaskar, S., Meripo, N.V., Konam, S., and Metze, F. (2020, January 4–8). Asr error correction and domain adaptation using machine translation. Proceedings of the ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9053126 ↗
18. Del Rio, M., Delworth, N., Westerman, R., Huang, M., Bhandari, N., Palakapilly, J., McNamara, Q., Dong, J., Zelasko, P., and Jetté, M. (2021). Earnings-21: A practical benchmark for ASR in the wild. arXiv.10.21437/Interspeech.2021-1915 ↗
19. Wang, H., Dong, S., Liu, Y., Logan, J., Agrawal, A.K., and Liu, Y. (2022, January 18–22). ASR Error Correction with Augmented Transformer for Entity Retrieval. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Incheon, Republic of Korea.
20. Das, N., Chau, D.H., Sunkara, M., Bodapati, S., Bekal, D., and Kirchhoff, K. (2022, January 23–27). Listen, Know and Spell: Knowledge-Infused Subword Modeling for Improving ASR Performance of OOV Named Entities. Proceedings of the ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore.10.1109/ICASSP43922.2022.9746748 ↗
21. Shukla, A., Bhattacharya, P., Poddar, S., Mukherjee, R., Ghosh, K., Goyal, P., and Ghosh, S. (2022). Legal case document summarization: Extractive and abstractive methods and their evaluation. arXiv.10.18653/v1/2022.aacl-main.77 ↗
22. Hellesoe, L.J. (2022). Automatic Domain-Specific Text Summarisation with Deep Learning Approaches. [Ph.D. Thesis, Auckland University of Technology].
23. Predicting judicial decisions of the European Court of Human Rights: A natural language processing perspective10.7717/peerj-cs.93 ↗
24. Trautmann, D., Petrova, A., and Schilder, F. (2022). Legal Prompt Engineering for Multilingual Legal Judgement Prediction. arXiv.
25. Hendrycks, D., Burns, C., Chen, A., and Ball, S. (2021). Cuad: An expert-annotated nlp dataset for legal contract review. arXiv.
26. Towards user-centered and legally relevant smart-contract development: A systematic literature review
27. Zheng, L., Guha, N., Anderson, B.R., Henderson, P., and Ho, D.E. (2021, January 21–25). When does pretraining help? assessing self-supervised learning for law and the casehold dataset of 53,000+ legal holdings. Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law, São Paulo, Brazil.10.1145/3462757.3466088 ↗
28. Rabelo, J., Kim, M., Goebel, R., Yoshioka, M., Kano, Y., and Satoh, K. (2024, June 19). COLIEE 2020: Methods for Legal Document Retrieval and Entailment. Available online: https://sites.ualberta.ca/~rabelo/COLIEE2021/COLIEE_2020_summary.pdf.10.1007/978-3-030-79942-7_13 ↗
29. Chalkidis, I., Fergadiotis, M., Manginas, N., Katakalou, E., and Malakasiotis, P. (2021). Regulatory compliance through Doc2Doc information retrieval: A case study in EU/UK legislation where text similarity has limitations. arXiv.10.18653/v1/2021.eacl-main.305 ↗
30. Kiyavitskaya, N., Zeni, N., Breaux, T.D., Antón, A.I., Cordy, J.R., Mich, L., and Mylopoulos, J. (2008, January 20–24). Automating the extraction of rights and obligations for regulatory compliance. Proceedings of the Conceptual Modeling-ER 2008: 27th International Conference on Conceptual Modeling, Barcelona, Spain. Proceedings 27.10.1007/978-3-540-87877-3_13 ↗
31. A normalized Levenshtein distance metric10.1109/TPAMI.2007.1078 ↗
32. Graves, A. (2012). Sequence transduction with recurrent neural networks. arXiv.10.1007/978-3-642-24797-2 ↗
33. Guo, J., Tiwari, G., Droppo, J., Van Segbroeck, M., Huang, C.W., Stolcke, A., and Maas, R. (2020). Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition. arXiv.10.21437/Interspeech.2020-1557 ↗
34. Rao, K., Sak, H., and Prabhavalkar, R. (2017, January 16–20). Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer. Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Okinawa, Japan.10.1109/ASRU.2017.8268935 ↗
35. Normalized (pointwise) mutual information in collocation extraction
36. Řehůřek, R., and Sojka, P. (2010, January 22). Software Framework for Topic Modelling with Large Corpora. Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, Valletta, Malta. Available online: http://is.muni.cz/publication/884893/en.
37. Agirre, E., Banea, C., Cardie, C., Cer, D., Diab, M., Gonzalez-Agirre, A., Guo, W., Mihalcea, R., Rigau, G., and Wiebe, J. (2014, January 23–24). Semeval-2014 task 10: Multilingual semantic textual similarity. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), Dublin, Ireland.10.3115/v1/S14-2010 ↗
38. Boteva, V., Gholipour, D., Sokolov, A., and Riezler, S. (2016, January 20–23). A Full-Text Learning to Rank Dataset for Medical Information Retrieval. Proceedings of the 38th European Conference on Information Retrieval, Padua, Italy. Available online: http://www.cl.uni-heidelberg.de/~riezler/publications/papers/ECIR2016.pdf.10.1007/978-3-319-30671-1_58 ↗
39. Thakur, N., Reimers, N., Rücklé, A., Srivastava, A., and Gurevych, I. (2021, January 6–14). BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), Online. Available online: https://openreview.net/forum?id=wCu6T5xFjeJ.
40. The probabilistic relevance framework: BM25 and beyond10.1561/1500000019 ↗
41. Pennington, J., Socher, R., and Manning, C.D. (2014, January 25–29). Glove: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.10.3115/v1/D14-1162 ↗
42. Pennington, J., Socher, R., and Manning, C.D. (2025, August 07). GloVe: Global Vectors for Word Representation. Available online: https://nlp.stanford.edu/projects/glove/.
43. Wang, W., Wei, F., Dong, L., Bao, H., Yang, N., and Zhou, M. (2020). MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers. arXiv.10.18653/v1/2021.findings-acl.188 ↗
44. Williams, C. (2007). Tradition and Change in Legal English: Verbal Constructions in Prescriptive Texts, Peter Lang.
45. Haigh, R. (2018). Legal English, Routledge.10.4324/9781315149127 ↗
46. Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Aletras, N., and Androutsopoulos, I. (2020, January 16–20). LEGAL-BERT: The Muppets straight out of Law School. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, Online.10.18653/v1/2020.findings-emnlp.261 ↗
47. Hofstätter, S., Lin, S.C., Yang, J.H., Lin, J., and Hanbury, A. (2021, January 11–15). Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event.10.1145/3404835.3462891 ↗
48. Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., and Yang, D. (2023). Is ChatGPT a general-purpose natural language processing task solver?. arXiv.10.18653/v1/2023.emnlp-main.85 ↗
49. Wang, J., Liang, Y., Meng, F., Shi, H., Li, Z., Xu, J., Qu, J., and Zhou, J. (2023). Is chatgpt a good nlg evaluator? a preliminary study. arXiv.10.18653/v1/2023.newsum-1.1 ↗
50. Törnberg, P. (2023). Chatgpt-4 outperforms experts and crowd workers in annotating political twitter messages with zero-shot learning. arXiv.
51. Cegin, J., Simko, J., and Brusilovsky, P. (2023). ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness. arXiv.10.18653/v1/2023.emnlp-main.117 ↗
52. Training language models to follow instructions with human feedback
53. Liu, F., Jiao, Y., Massiah, J., Yilmaz, E., and Havrylov, S. (2022). Trans-encoder: Unsupervised sentence-pair modelling through self-and mutual-distillations. arXiv.
54. Sanh, V., Debut, L., Chaumond, J., and Wolf, T. (2019). DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter. arXiv.
55. Carlsson, F., Gyllensten, A.C., Gogoulou, E., Hellqvist, E.Y., and Sahlgren, M. (2020, January 26–30). Semantic re-tuning with contrastive tension. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia.
56. Sanders, T. (2025, August 07). Customizing Embeddings, 2023. OpenAI. Available online: https://github.com/openai/openai-cookbook/blob/main/examples/Customizing_embeddings.ipynb.