{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T12:21:11Z","timestamp":1773490871647,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570744","type":"print"},{"value":"9789819570751","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-7075-1_34","type":"book-chapter","created":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:13:45Z","timestamp":1773486825000},"page":"523-536","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Phoneme-Based Optimization of\u00a0Enrollment Selection for\u00a0Speaker Identification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9838-2260","authenticated-orcid":false,"given":"Long-Quoc","family":"Le","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1185-2394","authenticated-orcid":false,"given":"Minh-Nhut","family":"Ngo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,15]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Mohd Hanifa, R., Isa, K., Mohamad, S.: A review on speaker recognition: technology and challenges. Comput. Electr. Eng. 90, 107005 (2021). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0045790621000318","DOI":"10.1016\/j.compeleceng.2021.107005"},{"issue":"4","key":"34_CR2","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors: robust DNN embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"34_CR4","first-page":"3560","volume":"2021","author":"N Dawalatabad","year":"2021","unstructured":"Dawalatabad, N., Ravanelli, M., Grondin, F., Thienpondt, J., Desplanques, B., Na, H.: ECAPA-TDNN embeddings for speaker diarization. Interspeech 2021, 3560\u20133564 (2021)","journal-title":"Interspeech"},{"key":"34_CR5","first-page":"1918","volume":"2023","author":"VT Pham","year":"2023","unstructured":"Pham, V.T., Nguyen, X.T.H., Hoang, V., Nguyen, T.T.T.: Vietnam-Celeb: a large-scale dataset for Vietnamese speaker recognition. Interspeech 2023, 1918\u20131922 (2023)","journal-title":"Interspeech"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Interspeech, pp. 3214\u20133218 (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"34_CR8","first-page":"2616","volume":"2017","author":"A Nagrani","year":"2017","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. Interspeech 2017, 2616\u20132620 (2017)","journal-title":"Interspeech"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, K., Wang, S., Li, H., Mak, M.-W., Lee, K.A.: On the effectiveness of enrollment speech augmentation for target speaker extraction. In: 2024 IEEE Spoken Language Technology Workshop (SLT), pp. 325\u2013332 (2024)","DOI":"10.1109\/SLT61566.2024.10832217"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Mingote, V., Miguel, A., Gim\u00e9nez, A.O., Lleida, E.: Training speaker enrollment models by network optimization. In: INTERSPEECH, pp. 3810\u20133814 (2020)","DOI":"10.21437\/Interspeech.2020-2325"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Le, L., Ngo, M.-N.: Data-centric optimization of enrollment selection in speaker identification. In: Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods \u2013 ICPRAM, INSTICC. SciTePress, pp. 344\u2013351 (2025)","DOI":"10.5220\/0013256800003905"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Garofolo, J., Lamel, L., Fisher, W., Fiscus, J., Pallett, D.: DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM. NIST speech disc 1-1.1,\u201d NASA STI\/Recon Technical Report N, vol. 93, p. 27403 (Jan 1993)","DOI":"10.6028\/NIST.IR.4930"},{"key":"34_CR13","first-page":"2247","volume":"2018","author":"Y Liu","year":"2018","unstructured":"Liu, Y., He, L., Liu, J., Johnson, M.T.: Speaker embedding extraction with phonetic information. Interspeech 2018, 2247\u20132251 (2018)","journal-title":"Interspeech"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: On the usage of phonetic information for text-independent speaker embedding extraction. In: Interspeech, pp. 1148\u20131152 (2019)","DOI":"10.21437\/Interspeech.2019-3036"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., He, L., Liu, J., Johnson, M.T.: Introducing phonetic information to speaker embedding for speaker verification. EURASIP J. Audio Speech Music Process. (2019)","DOI":"10.1186\/s13636-019-0166-8"},{"key":"34_CR16","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1109\/LSP.2022.3143036","volume":"29","author":"T Liu","year":"2022","unstructured":"Liu, T., Das, R.K., Lee, K.A., Li, H.: Neural acoustic-phonetic approach for speaker verification with phonetic attention mask. IEEE Signal Process. Lett. 29, 782\u2013786 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"34_CR17","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.1109\/TASLP.2023.3267833","volume":"31","author":"Q-B Hong","year":"2023","unstructured":"Hong, Q.-B., Wu, C.-H., Wang, H.-M.: Decomposition and reorganization of phonetic information for speaker embedding learning. IEEE\/ACM Trans. Audio, Speech Lang. Process. 31, 1745\u20131757 (2023)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process."},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Song, Z., He, L., Wang, P., Hu, Y., Huang, H.: Introducing multilingual phonetic information to speaker embedding for speaker verification. In: ICASSP 2024 \u2013 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10091\u201310095 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446546"},{"key":"34_CR19","doi-asserted-by":"publisher","first-page":"1513","DOI":"10.1121\/1.4906837","volume":"137","author":"V Dellwo","year":"2015","unstructured":"Dellwo, V., Leemann, A., Kolly, M.-J.: Rhythmic variability between speakers: articulatory, prosodic, and linguistic factors. J. Acoustical Soc. Am. 137, 1513 (2015)","journal-title":"J. Acoustical Soc. Am."},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an asr corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"34_CR21","volume-title":"Text-to-speech shared task in VLSP campaign 2019: evaluating Vietnamese speech synthesis on common datasets","author":"NTT Trang","year":"2019","unstructured":"Trang, N.T.T., Tung, N.X.: Text-to-speech shared task in VLSP campaign 2019: evaluating Vietnamese speech synthesis on common datasets. Vietnamese Language Signal Processing, VLSP (2019)"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Ngo, M.-N., Le, L.-Q.: Evaluation of command and speaker recognition on Vietnamese voice dataset to enhance security. In: 2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), pp. 1\u20136 (2024)","DOI":"10.1109\/MAPR63514.2024.10660987"},{"key":"34_CR23","unstructured":"Le, T.-T., Nguyen, L.T., Nguyen, D.Q.: PhoWhisper: automatic Speech Recognition for Vietnamese. In: Proceedings of the ICLR 2024 Tiny Papers track (2024)"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Tri, N.M., Nam, C.X., et al.: Vietnamese speech synthesis with end-to-end model and text normalization. In: 2020 7th NAFOSTED Conference on Information and Computer Science (NICS). IEEE, pp. 179\u2013184 (2020)","DOI":"10.1109\/NICS51282.2020.9335905"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7075-1_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:13:47Z","timestamp":1773486827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7075-1_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570744","9789819570751"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7075-1_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"15 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}