Multi-agent neurocognitive algorithm for controlling the reference of speech events of communication of a general artificial intelligence agent in a situation of synchronous multiple dialogues

Z.V. Nagoev, O.V. Nagoeva, D.G. Makoeva, I.A. Gurtueva

---

Abstract. Basic principles, models and algorithms for controlling the reference of speech messages have been developed based on the creation of a two-circuit model of multi-agent neurocognitive architecture – a superintellecton, which implements the interaction of the subconscious intellecton and the conscious intellecton. Requirements for ontologies of a general artificial intelligence agent, the conditions for their formation, and the functional units of neurocognitive architectures necessary for their effective formation in the training mode are outlined. The results obtained can be used to create speech recognition and understanding systems that are operational when used in noisy environments and situations of multiple synchronous dialogues to improve the quality of recognition using an understanding of the context of situations.

Keywords: artificial general intelligence, multi-agent systems, neurocognitive architectures, speech recognition, speech understanding

For citation. Nagoev Z.V., Nagoeva O.V., Makoeva D.G., Gurtueva I.A. Multi-agent neurocognitive algorithm for controlling the reference of speech events of communication of a general artificial intelligence agent in a situation of synchronous multiple dialogues. News of the Kabardino-Balkarian Scientific Center of RAS. 2023. No. 6(116). Pp. 193–209. DOI: 10.35330/1991-6639-2023-6-116-193-209

References

1. Nagoev Z.V. Intellektika, ili Myshleniye v zhivykh i iskusstvennykh sistemakh [Intelligence, or Thinking in living and artificial systems]. Nalchik: Izdatel’stvo KBNTS RAN, 2013. 232 p. (In Russian)
2. Cyrus H. Gordon. The Accidental Invention of the Phonemic Alphabet. Journal оf Near Eastern Studies. 1970. Vol. 29. No. 3. Pp. 193–197.
3. Russell S., Norvig P. Artificial Intelligence: A Modern Approach (AIMA). 2nd ed. Moscow: Williams, 2007. 1424 p.
4. Nagoev Z.V., Nagoeva O.V. Obosnovaniye simvolov i mul’tiagentnyye neyrokognitivnyye modeli semantiki yestestvennogo yazyka [Symbol grounding and multi-agent neurocognitive models of natural language semantics]. Nalchik: Izdatel’stvo KBNTS RAN, 2022. 150 p. (In Russian)
5. Nagoev Z., Nagoeva O., Anchekov M. et al. The symbol grounding problem in the system of general artificial intelligence based on multi-agent neurocognitive architecture. Cognitive Systems Researchthis link is disabled. 2023. No. 79. Pp. 71–84.
6. Nagoev Z., Pshenokova I., Nagoeva O., Sundukov Z. Learning algorithm for an intelligent decision making system based on multi-agent neurocognitive architectures. Cognitive Systems Research. Vol. 66. 2021. Pp. 82–88. ISSN 1389-0417. https://doi.org/10.1016/j.cogsys. 2020.10.015.
7. Nagoev Z., Nagoeva O., Gurtueva I. Multi-agent neurocognitive models of semantics of spatial localization of events. Cognitive Systems Research. 2020. Vol. 59. Pp. 91–102.
8. Nagoev Z., Gurtueva I., Malyshev D., Sundukov Z. Multi-agent algorithm imitating formation of phonemic awareness. Advances in Intelligent Systems and Computing. 2020. Vol. 948. Pp. 364–369.
9. Nagoev Z., Pshenokova I., Gurtueva I., Bzhikhatlov K. A simulation model for the cognitive function of static objects recognition based on machine-learning multi-agent architectures. Advances in Intelligent Systems and Computing. 2020. Vol. 948. Pp. 370–378.
10. Nagoev Z.V. Ontoneuromorphogenetic modeling. News of the Kabardino-Balkarian Scientific Center of RAS. 2013. No. 4(54). Pp. 46–56. (In Russian)
11. Hui P.-Y., Meng H. Latent Semantic Analysis for Multimodal User Input With Speech and Gestures. IEEE/ACM Transactions on Audio, Speech and Language Processing. 2014. Vol. 22. No. 2. Pp. 417–429.
12. Despotovic V., Walter O., Haeb-Umbach R. Machine learning techniques for semantic analysis of dysarthric speech: An experimental study. Speech Communication. 2018. Vol. 99. Pp. 242–251.

Information about the authors

Nagoev Zalimkhan Vyacheslavovich, Candidate of Technical Sciences, General Director of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 37-a I. Armand street;
zaliman@mail.ru, ORCID: https://orcid.org/0000-0001-9549-1823
Nagoeva Olga Vladimirovna, Researcher of the Department “Multiagent Systems”, Institute of Computer Science and Problems of Regional Management – branch of Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 37-a I. Armand street;
nagoeva_o@mail.ru, ORCID: https://orcid.org/0000-0003-2341-7960
Makoeva Dana Gisovna, Candidate of Philological Sciences, Head of the Laboratory of Computational Linguistics, Institute of Computer Science and Problems of Regional Management – branch of KabardinoBalkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 37-a I. Armand street;
makoevadana@mail.ru, ORCID: https://orcid.org/0000-0001-5955-2262
Gurtueva Irina Aslanbekovna, Researcher of the Laboratory of Computational Linguistics, Institute of Computer Science and Problems of Regional Management – branch of Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences;
360000, Russia, Nalchik, 37-a I. Armand street;
gurtueva-i@yandex.ru, ORCID: https://orcid.org/0000-0003-4945-5682