Integrating Apriori Mining and Speech Recognition for Intelligent and Secure Online Classroom Interaction
Abstract
Real-time structuring of speech and anomaly detection remain critical challenges in online classroom interactions, especially under noisy and multi-speaker conditions. This study proposes an integrated framework that combines Automatic Speech Recognition (ASR) with Apriori-based pattern mining to enhance the intelligence and security of online classrooms. The system first applies multi-speaker ASR with acoustic feature separation to achieve robust transcription, speaker labeling, and noise suppression. The transcribed text is pre-processed through Chinese word segmentation and stop-word filtering to construct a transactional dataset. Frequent Pattern Growth (FP-Growth) is then employed to generate frequent itemsets and extract high-confidence association rules, forming a reference speech-pattern library. Local anomaly factors are introduced to quantify deviations in support and confidence between new corpora and the rule library, thereby enabling early detection of sensitive or off-topic speech. Experimental validation on 120 classroom sessions demonstrates an 80.2% recognition accuracy in highly noisy environments, with rule coverage and confidence reaching 87% and 89%, respectively. The proposed framework significantly improves anomaly warning efficiency, reducing sensitive-speech combinations by 87.0%. These results highlight the feasibility and effectiveness of integrating ASR and Apriori mining for intelligent speech structuring, pattern extraction, and anomaly detection in secure online classroom environments.References
References
.Chen Y, Zhang J, Yuan X, et al. Sok: A modularized approach to study the security of automatic speech recognition systems[J]. ACM Transactions on Privacy and Security, 2022, 25(3): 1-31.
.Aldarwbi MY, Lashkari AH, Ghorbani A A. The sound of intrusion: A novel network intrusion detection system[J]. Computers and Electrical Engineering, 2022, 104: 108455.
.Zhang L. Data mining and learning behavior analysis of French online education data-driven teaching based on generative adversarial network improvement Apriori algorithm[J]. International Journal of Wireless and Mobile Computing, 2025, 28(2): 205-215.
.Onishi S, Yasumori T, Shiina H. Classroom Utterance Analysis and Visualization Using a Generative Deep Neural Networks for Dialogue Model[J]. International Journal of Smart Computing and Artificial Intelligence, 2024, 8(2).
.Chen Z, Han B, Wang S, et al. Attention-based encoder-decoder end-to-end neural diarization with embedding enhancer[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024, 32: 1636-1649.
.Gomez A, Pattichis MS, Celedón- Pattichis S. Speaker diarization and identification from single channel classroom audio recordings using virtual microphones[J]. IEEE Access, 2022, 10: 56256-56266.
.Ge Y, Zhao L, Wang Q, et al. Advddos : Zero-query adversarial attacks against commercial speech recognition systems[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 3647-3661.
.Lamichhane B. Speaker Diarization With Embeddings From a VGGish Model[J]. Dihardchallenge . Github . Io, 2024: 12-14.
.Kothalkar PV, Hansen JHL, Irvin D, et al. Child-adult speech diarization in naturalistic conditions of preschool classrooms using room-independent ResNet model and automatic speech recognition-based re-segmentation[J]. The Journal of the Acoustical Society of America, 2024, 155(2): 1198-1215.
.Xylogiannis P, Vryzas N, Vrysis L, et al. Multisensory fusion for unsupervised spatiotemporal speaker diarization [J]. Sensors, 2024, 24(13): 4229.
.Liu R, Shi J, Chen X, et al. Network anomaly detection and security defense technology based on machine learning: A review[J]. Computers and Electrical Engineering, 2024, 119: 109581.
.Bagui S S , Khan MP, Valmyr C, et al. Model Retraining upon Concept Drift Detection in Network Traffic Big Data[J]. Future Internet, 2025, 17(8): 328.
.Zheng G. Construction of ideological and political education in universities based on intelligent digital education[J]. Advances in Educational Technology and Psychology, 2024, 8(1): 45-54.
.Serafini L, Cornell S, Morrone G, et al. An experimental review of speaker diarization methods with application to two-speaker conversational telephone speech recordings[J]. Computer speech & language, 2023, 82: 101534.
.Southwell R, Pugh S, Perkoff M, et al. Challenges and feasibility of automatic speech recognition for modeling student collaborative discourse in classrooms[J]. International Educational Data Mining Society, 2022.
.Luo Y. Artificial intelligence model for real-time monitoring of ideological and political teaching system[J]. Journal of Intelligent & Fuzzy Systems, 2021, 40(2): 3585-3594.
.Zhan H, Meng X, Asif M. Risk early warning of a dynamic ideological and political education system based on LSTM-MLP: Online education data processing and optimization[J]. Mobile Networks and Applications, 2024, 29(2): 1 -13 .
.Cheng M, Lin Y, Li M. Sequence-to-sequence neural diarization with automatic speaker detection and representation[J]. IEEE Transactions on Audio, Speech and Language Processing, 2025.
.Bois A, Tervil B, Oudre L. A persistent homology-based algorithm for unsupervised anomaly detection in time series[J]. Transactions on Machine Learning Research, 2024.
.Wang J., Dudy S., He X., Wang Z., Southwell R., & Whitehill J. Optimizing Speaker Diarization for the Classroom: Applications in Timing Student Speech and Distinguishing Teachers from Children[J]. Journal of Educational Data Mining, 2025, 17(1): 98-125.
.Cai J, Li Y. Fuzzy association rule mining for Personalized English Language Teaching from higher education[J]. Journal of Computational Methods in Sciences and Engineering, 2024, 24(6): 3617-3631.
.Essalmi H, El Affar A. Dynamic Algorithm for Mining Relevant Association Rules via Meta-Patterns and Refinement-Based Measures[J]. Information, 2025, 16(6): 438 -467 .
.Sun Z, Peng Q, Mou X, et al. An artificial intelligence-based real-time monitoring framework for time series[J]. Journal of Intelligent & Fuzzy Systems, 2021, 40(6): 10401-10415.
.Ryan S, Djukic P, Morris T, et al. Pattern detection in time-series data: US Patent 11,620,528[P]. 2023-4-4.
.Janský J, Koldovský Z, Málek J, et al. Auxiliary function-based algorithm for blind extraction of a moving speaker[J]. EURASIP Journal on Audio, Speech, and Music Processing, 2022, 2022(1): 1.
.Schwartz A, Schwartz O, Chazan SE, et al. Multi-microphone simultaneous speakers detection and localization of multi-sources for separation and noise reduction[J]. EURASIP Journal on Audio, Speech, and Music Processing, 2024, 2024(1): 50.
.Tian J, Yu J, Weng C, et al. Improving mandarin end-to-end speech recognition with word n-gram language model[J]. IEEE Signal Processing Letters, 2022, 29: 812-816.
.Kim M, Jang G J. Speaker-Attributed Training for Multi-Speaker Speech Recognition Using Multi-Stage Encoders and Attention-Weighted Speaker Embedding[J]. Applied Sciences, 2024, 14(18): 8138.
.Huang Z, Delcroix M, Garcia LP, et al. Joint speaker diarization and speech recognition based on region proposal networks[J]. Computer Speech & Language, 2022, 72: 101316.
.He MK, Du J, Liu QF, et al. Ansd -ma- mse : Adaptive neural speaker diarization using memory-aware multi-speaker embedding[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023, 31: 1561-1573.
DOI:
https://doi.org/10.31449/inf.v49i37.11444Downloads
Published
How to Cite
Issue
Section
License
I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.
I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.
In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.
I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.
Copyright © Slovenian Society Informatika
