Research on Speech Rehabilitation Assessment Models Based on Natural Language Processing
DOI:
https://doi.org/10.63313/hmt.9014Keywords:
Speech rehabilitation assessment, Deep learning, Hybrid neural network, Speech analysis, Rehabilitation training systemAbstract
Artificial intelligence technologies present new developmental opportunities within the medical rehabilitation field. Addressing challenges in speech rehabilitation assessment—such as inefficient manual evaluation and inconsistent standards—this paper designs an intelligent assessment model grounded in deep learning. Employing a hybrid CNN+BiLSTM+Attention architecture, the model achieves multidimensional feature extraction and analysis of speech signals, establishing an evaluation system covering dimensions such as articulation, fluency, and prosody. Clinical validation demonstrates that this model significantly enhances assessment efficiency and accuracy, providing effective technical support for speech rehabilitation training.
References
[1] Celesti A, Fazio M, Carnevale L, et al. A NLP-based approach to improve speech recognition services for people with speech disorders[C]//2022 IEEE Symposium on Computers and Communications (ISCC). IEEE, 2022: 1-6.
[2] Zhou B, Yang G, Shi Z, et al. Natural language processing for smart healthcare[J]. IEEE Re-views in Biomedical Engineering, 2022, 17: 4-18.
[3] Aramaki E, Wakamiya S, Yada S, et al. Natural language processing: from bedside to eve-rywhere[J]. Yearbook of medical informatics, 2022, 31(01): 243-253.
[4] Pandey S, Sharma S, Wazir S. Mental healthcare chatbot based on natural language pro-cessing and deep learning approaches: Ted the therapist[J]. International Journal of Infor-mation Technology, 2022, 14(7): 3757-3766.
[5] Flores D F C, Arias I F B, Miranda M E I, et al. Applying Neutrosophic Natural Language Processing to Analyze Complex Phenomena in Interdisciplinary Contexts[J]. Neutrosophic Sets and Systems, 2024, 74: 297-305.
[6] Dougherty R F, Clarke P, Atli M, et al. Psilocybin therapy for treatment resistant depression: prediction of clinical outcome by natural language processing[J]. Psychopharmacology, 2025, 242(7): 1553-1561.
[7] Nair V K K, Farah W, Cushing I. A critical analysis of standardized testing in speech and language therapy[J]. Language, Speech, and Hearing Services in Schools, 2023, 54(3): 781-793.
[8] Shetty P, Udhayakumar R, Patil A, et al. Application of natural language processing (NLP) in machine learning[C]//2023 3rd International Conference on Advancement in Electron-ics & Communication Engineering (AECE). IEEE, 2023: 949-957.
[9] Hauser T U, Skvortsova V, De Choudhury M, et al. The promise of a model-based psychia-try: building computational models of mental ill health[J]. The Lancet Digital Health, 2022, 4(11): e816-e828.
[10] Houssein E H, Mohamed R E, Ali A A. Machine learning techniques for biomedical natural language processing: a comprehensive review[J]. IEEE access, 2021, 9: 140628-140653.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by author(s) and Erytis Publishing Limited.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
