Interpretable Machine Learning-Enabled Time-Resolved Speech Command Recognition Using Triboelectric Laminate Acoustic Sensors
ACS Applied Electronic Materials · 10.11.2026 · 8 (21) · 9409-9420
DOI: 10.1021/acsaelm.6c01520 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Applied Electronic Materials, online erschienen am 21.10.2026. Verfasst von Anand Babu und 7 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Gefördert von: Ministry of Electronics and Information technology, Ministry of Education, European Regional Development Fund.
Abstract (Originalsprache)
The growth of wearable electronics has intensified the search for sustainable, high-performance materials for integration into smart sensing platforms. Conventional piezoelectric polymers, particularly fluorinated systems, offer excellent electromechanical transduction; however, they pose environmental and end-of-life challenges. Here, we demonstrate a recycled expanded polystyrene (PS) triboelectric laminate as an acoustic neuromorphic sensor. The multilayered structure of the triboelectric laminate enables a mechanoelectric response similar to that of piezoelectric polymers. The triboelectric laminate sensor was integrated into the face mask and generated current signals in the range of 4 nA (peak-to-peak) with distinct features in response to speech signals of various words. To exploit the recorded signals for dynamic speech recognition, we develop an interpretable physics-guided staged ML framework named Triboelectric Lexical Network (TriboLexNet), which learns the spectral signatures and combines time-frequency descriptors embedded into a random-forest framework. TriboLexNet is capable to recognize the specific word in the sentences, with a held-out segment-level accuracy of 99.4 ± 0.9% and a per-recording keyword-detection accuracy of 89.6 ± 6.4% under strict recording-level data partitioning, as well as locating it in terms of an interpretable probability distribution. Our approach establishes a viable platform for sustainable triboelectric acoustic neuromorphic sensing and demonstrates how physics-guided ML can be utilized in dynamic speech recognition with limited data.
Förderung
- Ministry of Electronics and Information technology
- Ministry of Education
- European Regional Development Fund
- Ministry of Science and ICT, South Korea
- Ministry of Trade, Industry and Energy
Zitieren
APA
Babu, A., Šutka, A., Lee, Y., Linarts, A., Sherrell, P. C., Mandal, D., Jeong, C. K., & Šutka, A. (2026). Interpretable Machine Learning-Enabled Time-Resolved Speech Command Recognition Using Triboelectric Laminate Acoustic Sensors. ACS Applied Electronic Materials, 8(21), 9409-9420. https://doi.org/10.1021/acsaelm.6c01520
Vancouver
Babu A, Šutka A, Lee Y, Linarts A, Sherrell PC, Mandal D, et al. Interpretable Machine Learning-Enabled Time-Resolved Speech Command Recognition Using Triboelectric Laminate Acoustic Sensors. ACS Applied Electronic Materials. 2026;8(21):9409-9420. doi:10.1021/acsaelm.6c01520
BibTeX
@article{Babu2026,
author = {Babu, Anand and Šutka, Anna and Lee, Yebin and Linarts, Artis and Sherrell, Peter C. and Mandal, Dipankar and Jeong, Chang Kyu and Šutka, Andris},
title = {Interpretable Machine Learning-Enabled Time-Resolved Speech Command Recognition Using Triboelectric Laminate Acoustic Sensors},
journal = {ACS Applied Electronic Materials},
year = {2026},
volume = {8},
number = {21},
pages = {9409--9420},
doi = {10.1021/acsaelm.6c01520}
}
EUVIMED