{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:37:32Z","timestamp":1786534652200,"version":"build-2736575974"},"reference-count":33,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["31920260116"],"award-info":[{"award-number":["31920260116"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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 \u00b1 2.14% on seen_test, 26.51 \u00b1 3.42% on unseen_test, and 72.10 \u00b1 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 \u00b1 2.71% to 35.25 \u00b1 4.17% and the Recall from 18.48 \u00b1 2.98% to 33.85 \u00b1 8.22%; the corresponding seed-level 95% confidence intervals were 24.89\u201345.61% and 13.43\u201354.27%. These results establish strong familiar-query discrimination, an audited fixed-threshold evaluation protocol, and partial, seed-sensitive transfer to held-out written queries.<\/jats:p>","DOI":"10.3390\/s26165107","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:02:11Z","timestamp":1786532531000},"page":"5107","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tibetan-PASEM: Phonology-Aware Speech Evidence Matching for Low-Resource Tibetan Written-Query Keyword Spotting"],"prefix":"10.3390","volume":"26","author":[{"given":"Yanze","family":"Guo","sequence":"first","affiliation":[{"name":"China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China"},{"name":"Key Laboratory of China\u2019s Ethnic Languages and Culture Computing, Ministry of Education, Lanzhou 730030, China"},{"name":"Data Intelligence Laboratory for Tibetan Plateau Human-Environment Systems, Lanzhou 730000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingmeng","family":"Guo","sequence":"additional","affiliation":[{"name":"China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China"},{"name":"Key Laboratory of China\u2019s Ethnic Languages and Culture Computing, Ministry of Education, Lanzhou 730030, China"},{"name":"Data Intelligence Laboratory for Tibetan Plateau Human-Environment Systems, Lanzhou 730000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zengguang","family":"Li","sequence":"additional","affiliation":[{"name":"China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China"},{"name":"Key Laboratory of China\u2019s Ethnic Languages and Culture Computing, Ministry of Education, Lanzhou 730030, China"},{"name":"Data Intelligence Laboratory for Tibetan Plateau Human-Environment Systems, Lanzhou 730000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Song","sequence":"additional","affiliation":[{"name":"China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China"},{"name":"Key Laboratory of China\u2019s Ethnic Languages and Culture Computing, Ministry of Education, Lanzhou 730030, China"},{"name":"Data Intelligence Laboratory for Tibetan Plateau Human-Environment Systems, Lanzhou 730000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Gong","sequence":"additional","affiliation":[{"name":"China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China"},{"name":"Key Laboratory of China\u2019s Ethnic Languages and Culture Computing, Ministry of Education, Lanzhou 730030, China"},{"name":"Data Intelligence Laboratory for Tibetan Plateau Human-Environment Systems, Lanzhou 730000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanyu","family":"Li","sequence":"additional","affiliation":[{"name":"China Institute of National Information Technology, Northwest Minzu University, Lanzhou 730030, China"},{"name":"Key Laboratory of China\u2019s Ethnic Languages and Culture Computing, Ministry of Education, Lanzhou 730030, China"},{"name":"Data Intelligence Laboratory for Tibetan Plateau Human-Environment Systems, Lanzhou 730000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chen, G., Parada, C., and Heigold, G. (2014). Small-Footprint Keyword Spotting Using Deep Neural Networks. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, 4\u20139 May 2014, IEEE.","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., and Parada, C. (2015). Convolutional Neural Networks for Small-Footprint Keyword Spotting. Proceedings of the Interspeech 2015, Dresden, Germany, 6\u201310 September 2015, ISCA.","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Arik, S.O., Kliegl, M., Child, R., Hestness, J., Gibiansky, A., Fougner, C., Prenger, R., and Coates, A. (2017). Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting. Proceedings of the Interspeech 2017, Stockholm, Sweden, 20\u201324 August 2017, ISCA.","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"ref_4","unstructured":"Warden, P. (2018). Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition. arXiv."},{"key":"ref_5","unstructured":"de Andrade, D.C., Leo, S., Viana, M.L.D.S., and Bernkopf, C. (2018). A Neural Attention Model for Speech Command Recognition. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Jung, J., Kim, Y., Park, J., Lim, Y., Kim, B.-Y., Jang, Y., and Chung, J.S. (2023). Metric Learning for User-Defined Keyword Spotting. Proceedings of the ICASSP 2023, Rhodes Island, Greece, 4\u201310 June 2023, IEEE.","DOI":"10.1109\/ICASSP49357.2023.10096596"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, G., Parada, C., and Sainath, T.N. (2015). Query-by-Example Keyword Spotting Using Long Short-Term Memory Networks. Proceedings of the ICASSP 2015, Brisbane, Australia, 19\u201324 April 2015, IEEE.","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sacchi, N., Nanchen, A., Jaggi, M., and Cernak, M. (2019). Open-Vocabulary Keyword Spotting with Audio and Text Embeddings. Proceedings of the Interspeech 2019, Graz, Austria, 15\u201319 September 2019, ISCA.","DOI":"10.21437\/Interspeech.2019-1846"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Lee, Y.-H., and Cho, N. (2023). PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords. Proceedings of the Interspeech 2023, Dublin, Ireland, 20\u201324 August 2023, ISCA.","DOI":"10.21437\/Interspeech.2023-597"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Shin, H.-K., Han, H., Kim, D., Chung, S.-W., and Kang, H.-G. (2022). Learning Audio-Text Agreement for Open-Vocabulary Keyword Spotting. Proceedings of the Interspeech 2022, Incheon, Republic of Korea, 18\u201322 September 2022, ISCA.","DOI":"10.21437\/Interspeech.2022-580"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Navon, A., Shamsian, A., Glazer, N., Hetz, G., and Keshet, J. (2024). Open-Vocabulary Keyword-Spotting with Adaptive Instance Normalization. Proceedings of the ICASSP 2024, Seoul, Republic of Korea, 14\u201319 April 2024, ISCA.","DOI":"10.1109\/ICASSP48485.2024.10446912"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ai, Z., Chen, Z., and Xu, S. (2024, January 1\u20135). MM-KWS: Multi-Modal Prompts for Multilingual User-Defined Keyword Spotting. Proceedings of the Interspeech 2024, Kos Island, Greece.","DOI":"10.21437\/Interspeech.2024-10"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Chang, X., Qian, Y., and Yu, K. (2016). Unrestricted Vocabulary Keyword Spotting Using LSTM-CTC. Proceedings of the Interspeech 2016, San Francisco, CA, USA, 8\u201312 September 2016, ISCA.","DOI":"10.21437\/Interspeech.2016-753"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Reuter, P.M., Rollwage, C., and Meyer, B.T. (2023, January 4\u201310). Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-Embedding Mapping. Proceedings of the ICASSP 2023, Rhodes Island, Greece.","DOI":"10.1109\/ICASSP49357.2023.10095400"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, K., Zhou, H., Shen, K., Dai, Y., and Du, J. (2025, January 6\u201311). Phoneme-Level Contrastive Learning for User-Defined Keyword Spotting with Flexible Enrollment. Proceedings of the ICASSP 2025, Hyderabad, India.","DOI":"10.1109\/ICASSP49660.2025.10888312"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Yang, S., Oh, J., Kim, M., and Lee, J. (2022, January 18\u201322). Personalized Keyword Spotting through Multi-Task Learning. Proceedings of the Interspeech 2022, Incheon, Republic of Korea.","DOI":"10.21437\/Interspeech.2022-947"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Nishu, K., Cho, M., and Naik, D. (2023). Matching Latent Encoding for Audio-Text Based Keyword Spotting. Proceedings of the Interspeech 2023, Dublin, Ireland, 20\u201324 August 2023, ISCA.","DOI":"10.21437\/Interspeech.2023-478"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., and Schmidhuber, J. (2006). Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks. Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, USA, 25\u201329 June 2006, Association for Computing Machinery.","DOI":"10.1145\/1143844.1143891"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., and Wu, Y. (2020). Conformer: Convolution-Augmented Transformer for Speech Recognition. Proceedings of the Interspeech 2020, Shanghai, China, 25\u201329 October 2020, ISCA.","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref_20","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 2017, NeurIPS Foundation."},{"key":"ref_21","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume":"Volume 33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce, C., Caruana, R., and Niculescu-Mizil, A. (2006). Model Compression. Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, 20\u201323 August 2006, Association for Computing Machinery.","DOI":"10.1145\/1150402.1150464"},{"key":"ref_24","unstructured":"OpenSLR (2026, June 26). TIBMD@MUC Speech Data Set, SLR124. Available online: https:\/\/www.openslr.org\/124\/."},{"key":"ref_25","unstructured":"OpenSLR (2026, June 26). XBMU-AMDO31, SLR133. Available online: https:\/\/www.openslr.org\/133\/."},{"key":"ref_26","unstructured":"OpenSLR (2026, June 26). Tibetan Greetings, SLR149. Available online: https:\/\/www.openslr.org\/149\/."},{"key":"ref_27","unstructured":"OpenSLR (2026, June 26). NICT-Tib1: Lhasa-Tibetan Read-Speech Corpus, SLR158. Available online: https:\/\/www.openslr.org\/158\/."},{"key":"ref_28","unstructured":"Tournadre, N., and Suzuki, H. (2023). The Tibetic Languages: An Introduction to the Family of Languages Derived from Old Tibetan, LACITO."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tournadre, N. (2014). The Tibetic Languages and Their Classification. Trans-Himalayan Linguistics, De Gruyter Mouton.","DOI":"10.1515\/9783110310832.105"},{"key":"ref_30","unstructured":"Xie, C., Li, G., Ma, L., Sun, Q., and Guo, Y. (2025). XBMU-AMDO31: A Speech Recognition Dataset for the Amdo Dialect of Tibetan, Science Data Bank. Version 1."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Soky, K., Gong, Z., and Li, S. (2022, January 24\u201326). NICT-TIB1: A Public Speech Corpus of Lhasa Dialect for Benchmarking Tibetan Language Speech Recognition Systems. Proceedings of the Oriental COCOSDA 2022, Hanoi, Vietnam.","DOI":"10.1109\/O-COCOSDA202257103.2022.9997917"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.specom.2013.07.008","article-title":"Automatic Speech Recognition for Under-Resourced Languages: A Survey","volume":"56","author":"Besacier","year":"2014","journal-title":"Speech Commun."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wang, J., Xu, M., Hou, J., Zhang, B., Zhang, X.-L., Xie, L., and Pan, F. (2023). WeKws: A Production First Small-Footprint End-to-End Keyword Spotting Toolkit. Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 4\u201310 June 2023, IEEE.","DOI":"10.1109\/ICASSP49357.2023.10096736"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5107\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T11:05:33Z","timestamp":1786532733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":33,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165107"],"URL":"https:\/\/doi.org\/10.3390\/s26165107","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]}}}