OmniScience: A Multi-disciplinary Journal Original Research
MemorialBot: An AI-Powered Voice Cloning and Conversational System for Digital Legacy Preservation
Abstract
MemorialBot is a kind of AI technology that allows people, who have lost a loved one, to continue a conversation with the help of their voice. The dialogue will be with a simulated image of the deceased individual based on an amalgamation of audio recording, correspondence, and common life history. The technical design allows voice recognition technology, large language models to generate responses based on personalized knowledge bases, neural text-to-speech systems and voice cloning technology. The mean opinion score of 4.2 of 5.0 on voice naturalness and 82 percent on persona consistency were the results of the evaluation conducted by independent evaluators. Ethical concerns of informed consent, data privacy and psychological health are discussed. MemorialBot belongs to a new field of convergence between affective computing, grief technology, and digital heritage conservation.
Keywords
References (12)
- Savin-Baden M, Burden D. Digital Immortality and Virtual Humans. Postdigital Science and Education. 2018 Sept 27;1(1):87–103. Available from: https://link.springer.com/article/10.1007/s42438-018-0007-6
- Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S. Language models are few-shot learners. Advances in neural information processing systems. 2020;33:1877-901.
- Payne M. DYING, DEATH AND GRIEF IN AN ONLINE UNIVERSE: FOR COUNSELORS AND EDUCATORS. Journal of Technology in Human Services. 2012 Apr;30(2):137–9.
- Park G, Chung J, Lee S. Effect of AI chatbot emotional disclosure on user satisfaction and reuse intention for mental health counseling: A serial mediation model. Current Psychology. 2023 Nov;42(32):28663-73.
- Panayotov V, Chen G, Povey D, Khudanpur S. Librispeech: An ASR corpus based on public domain audio books. 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) [Internet]. 2015 Apr [cited 2026 Sept 7];5206–10. Available from: https://ijisae.org/index.php/IJISAE/article/view/7288
- 6. Papneja H, Yadav N. Self-disclosure to conversational AI: a literature review, emergent framework, and directions for future research. Personal and ubiquitous computing. 2025 Apr;29(2):119-51.
- Ankomah E, Turkson R. Emotion-aware AI chatbots for mental health support in low-resource public health systems: A case study from Ghana. World Journal of Public Health. 2025;10(3):17-29.
- Olivia Yan Huang Affiliation: University of Illinois Urbana-Champaign , USA email: yan65@illinois.edu, Monika Stodolska Affiliation: University of Illinois Urbana-Champaign , USA email: stodolsk@illinois.edu, Sharifa Sultana Affiliation: University of Illinois Urbana-Champaign , USA email: sharifas@illinois.edu. Emotional Support with Conversational AI: Talking to Machines About Life. Arxiv.org. 2026. Available from: https://arxiv.org/html/2603.22618v1
- 9. Casanova E, Weber J, Shulby CD, Junior AC, Gölge E, Ponti MA. Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone. InInternational conference on machine learning 2022 Jun 28 (pp. 2709-2720). PMLR.
- Iyer V. Federated Learning for Secure and Privacy-Preserving Voice Assistant Search. International Journal of Machine Learning and Predictive Analytics. 2019;2:01–9. Available from:https://www.researchgate.net/publication/410855854_Federated_Learning_for_Secure_and_Privacy-Preserving_Voice_Assistant_Search
- 11. Jain A, Gupta R. Voice-based digital heritage preservation using deep learning architectures. IEEE Transactions on Affective Computing. 2023; 14(3): 1124–1135.
- Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S, Bikel D. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288. 2023 Jul 18.