ARTIFICIAL INTELLIGENCE TRANSFORMER IN VOICE INTERACTION DESIGN AND SPEECH RECOGNITION FOR ELDERLY USERS UNDER THE DFSMN MODEL
- 28 March 2026
- journal article
- Published by World Scientific Pub Co Pte Ltd in Journal of Mechanics in Medicine and Biology
- Vol. 26 (04)
Abstract
This study focuses on the speech interaction experience of elderly users and proposes a speech recognition architecture, Con-DFSMN, which integrates a Convolution-augmented Transformer (Conformer) and Deep Feedforward Sequential Memory Network (DFSMN). The aim is to enhance recognition accuracy and system stability in variable and complex speech environments. The Additive Margin-Circle Loss (AM-Circle Loss) compound loss function is introduced, which effectively enhances the ability to distinguish class boundaries. This enables the model to exhibit excellent generalization performance when processing speech with high intra-class fluctuation and ambiguous boundaries. For the Tsinghua Chinese 30-hour Speech Corpus (THCHS-30) and DementiaBank datasets, experimental results show that Con-DFSMN achieves accuracies of 95.3% and 91.8% in short speech recognition, respectively, representing a 13.1% improvement over traditional Transformer models. Con-DFSMN also maintains advantages in long speech recognition, with maximum accuracies of 90.8% and 87.3%. During training, Con-DFSMN demonstrates faster convergence speed and more stable loss decline, advancing 15 epochs earlier than Deepspeech2 and improving by approximately 25% compared to Transformer. The results verify the effectiveness and robustness of the model, demonstrating its adaptability to the speech features of the elderly, laying a foundation for the development of intelligent elderly speech interaction systems.Keywords
Funding Information
- Youth Fund of Humanities and Social Sciences of the Ministry of Education of China (21YJC760102)
This publication has 38 references indexed in Scilit:
- An End-to-End Continuous Speech Recognition System in Bengali for General and Elderly DomainSN Computer Science, 2025
- Evaluating the efficacy of Amanda: A voice-based large language model chatbot for relationship challengesComputers in Human Behavior: Artificial Humans, 2025
- Sla-former: conformer using shifted linear attention for audio-visual speech recognitionComplex & Intelligent Systems, 2024
- Tran-DSR: A hybrid model for dysarthric speech recognition using transformer encoder and ensemble learningApplied Acoustics, 2024
- Effects of AI understanding-training on AI literacy, usage, self-determined interactions, and anthropomorphization with voice assistantsComputers and Education Open, 2024
- Attention‐Based End‐to‐End Automatic Speech Recognition System for Vulnerable Individuals in Tamil2024
- Long-term cognition and speech recognition outcomes after cochlear implantation in the elderlyAmerican Journal of Otolaryngology, 2023
- Developing sequentially trained robust Punjabi speech recognition system under matched and mismatched conditionsComplex & Intelligent Systems, 2022
- Bimodal variational autoencoder for audiovisual speech recognitionMachine Learning, 2021
- A modified feature selection method based on metaheuristic algorithms for speech emotion recognitionApplied Acoustics, 2021