Tibetan-PASEM: Phonology-Aware Speech Evidence Matching for Low-Resource Tibetan Written-Query Keyword Spotting
Sensors · 12.08.2026 · 26 (16) · 5107
DOI: 10.3390/s26165107 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 12.08.2026. Verfasst von Yanze Guo und 5 weiteren Autor:innen. Beteiligte Einrichtung: China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China. Hauptthemen laut MEDLINE: Phonetics, Speech, Speech Recognition Software. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Low-resource written-query keyword spotting detects a text-specified target in speech without spoken enrollment or full automatic speech recognition. We present Tibetan Phonology-Aware Speech Evidence Matching (Tibetan-PASEM), a method that encodes graphemic, approximate phonological, and dialect-related query information, matches it with local acoustic windows, aggregates window-level evidence, and applies a validation-selected operating point. Querybank198 contains 198 Tibetan written queries derived from four public speech resources. A complete-file and decoded pulse-code modulation (PCM) audit produced a corrected 213,128-pair evaluation with no identified recording-content, source-qualified speaker, or session-proxy overlap across the development-to-held-out boundary. In a three-seed corrected-index re-evaluation, the acoustically strengthened PASEM (PASEM-AS) achieved F1 scores of 66.16 ± 2.14% on seen_test, 26.51 ± 3.42% on unseen_test, and 72.10 ± 1.39% on the confusable-negative diagnostic condition, which comprises 20 training-exposed query forms and is used for negative-set analysis rather than difficulty ranking. Under the original pre-correction pair index, PASEM with transfer regularization (PASEM-TR) increased the unseen_test F1 from 25.80 ± 2.71% to 35.25 ± 4.17% and the Recall from 18.48 ± 2.98% to 33.85 ± 8.22%; the corresponding seed-level 95% confidence intervals were 24.89–45.61% and 13.43–54.27%. These results establish strong familiar-query discrimination, an audited fixed-threshold evaluation protocol, and partial, seed-sensitive transfer to held-out written queries.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China.
- Key Laboratory of China's Ethnic Languages and Culture Computing, Ministry of Education, Lanzhou 730030, China.
- Data Intelligence Laboratory for Tibetan Plateau Human-Environment Systems, Lanzhou 730000, China.
Förderung
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Guo, Y., Guo, X., Li, Z., Song, J., Gong, Y., & Li, G. (2026). Tibetan-PASEM: Phonology-Aware Speech Evidence Matching for Low-Resource Tibetan Written-Query Keyword Spotting. Sensors, 26(16), 5107. https://doi.org/10.3390/s26165107
Vancouver
Guo Y, Guo X, Li Z, Song J, Gong Y, Li G. Tibetan-PASEM: Phonology-Aware Speech Evidence Matching for Low-Resource Tibetan Written-Query Keyword Spotting. Sensors. 2026;26(16):5107. doi:10.3390/s26165107
BibTeX
@article{Guo2026,
author = {Guo, Yanze and Guo, Xingmeng and Li, Zengguang and Song, Jiaxin and Gong, Yuyang and Li, Guanyu},
title = {Tibetan-PASEM: Phonology-Aware Speech Evidence Matching for Low-Resource Tibetan Written-Query Keyword Spotting},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5107},
doi = {10.3390/s26165107}
}
EUVIMED