{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:54:47Z","timestamp":1776444887828,"version":"3.51.2"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"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\/978-3-032-07956-5_23","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:10Z","timestamp":1760253550000},"page":"322-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Language-Specific Adaptation Strategies for\u00a0Speaker Recognition Using MobileNet"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6125-9898","authenticated-orcid":false,"given":"Anton","family":"Yakovenko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evgeny","family":"Bessonnitsyn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5309-2207","authenticated-orcid":false,"given":"Valeria","family":"Efimova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9084-3604","authenticated-orcid":false,"given":"Mark","family":"Zaslavskiy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"23_CR1","doi-asserted-by":"publisher","first-page":"116649","DOI":"10.1109\/ACCESS.2024.3443811","volume":"12","author":"V Brydinskyi","year":"2024","unstructured":"Brydinskyi, V., Sabodashko, D., Khoma, Y., Podpora, M., Konovalov, A., Khoma, V.: Enhancing automatic speech recognition with personalized models: improving accuracy through individualized fine-tuning. IEEE Access 12, 116649\u2013116656 (2024)","journal-title":"IEEE Access"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Gu, Y., Du, Z., Zhang, S., Han, J., He, Y.: Personality-memory gated adaptation: an efficient speaker adaptation for personalized end-to-end automatic speech recognition. In: Proceedings of the Interspeech 2024, 1\u20135 September 2024, Kos Island, Greece, pp. 2870\u20132874 (2024)","DOI":"10.21437\/Interspeech.2024-1621"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Kang, Z., Wang, J., Peng, J., Xiao, J.: SVVAD: personal voice activity detection for speaker verification. In: Proceedings of the Interspeech 2023, 20\u201324 August 2023, Dublin, Ireland, pp. 5067\u20135071 (2023)","DOI":"10.21437\/Interspeech.2023-2413"},{"key":"23_CR4","unstructured":"Tran, K.: From English To foreign languages: transferring pre-trained language models (2020). https:\/\/arxiv.org\/abs\/2002.07306. Accessed 27 June 2025"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Luo, Jet al.: Cross-language transfer learning and domain adaptation for end-to-end automatic speech recognition. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), 5\u20139 July 2021, Shenzhen, China, pp. 1\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428334"},{"key":"23_CR6","doi-asserted-by":"publisher","first-page":"108998","DOI":"10.1016\/j.engappai.2024.108998","volume":"136","author":"L Lazzaroni","year":"2024","unstructured":"Lazzaroni, L., Bellotti, F., Berta, R.: An embedded end-to-end voice assistant. Eng. Appl. Artif. Intell. 136, 108998 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"23_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/978-3-319-40663-3_9","volume-title":"Advances in Neural Networks \u2013 ISNN 2016","author":"A Yakovenko","year":"2016","unstructured":"Yakovenko, A., Malychina, G.: Text-independent speaker recognition using radial basis function network. In: Cheng, L., Liu, Q., Ronzhin, A. (eds.) ISNN 2016. LNCS, vol. 9719, pp. 74\u201381. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-40663-3_9"},{"key":"23_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-030-37352-8_37","volume-title":"Cyberspace Safety and Security","author":"H Ai","year":"2019","unstructured":"Ai, H., Xia, W., Zhang, Q.: Speaker recognition based on lightweight neural network for smart home solutions. In: Vaidya, J., Zhang, X., Li, J. (eds.) CSS 2019. LNCS, vol. 11983, pp. 421\u2013431. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-37352-8_37"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Nunes, J.A.C., Mac\u00eado, D., Zanchettin, C.: Am-mobileNet1D: a portable model for speaker recognition. In: 2020 International Joint Conference on Neural Networks (IJCNN), 19\u201324 July 2020, Glasgow, United Kingdom, pp. 1\u20138 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207519"},{"key":"23_CR10","doi-asserted-by":"publisher","first-page":"3532","DOI":"10.1109\/TASLP.2024.3419426","volume":"32","author":"D Cai","year":"2024","unstructured":"Cai, D., Li, M.: Leveraging ASR pretrained conformers for speaker verification through transfer learning and knowledge distillation. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 3532\u20133545 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"23_CR11","doi-asserted-by":"publisher","first-page":"4226","DOI":"10.1109\/TASLP.2024.3463430","volume":"32","author":"V Kumar","year":"2024","unstructured":"Kumar, V., Abrol, V., Doss, M.M.: On the quantization of neural models for speaker verification. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 4226\u20134236 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., Fei Chiu, A.Y., Lee, T.: An investigation of reprogramming for cross-language adaptation in speaker verification systems. In: IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP), 7\u201310 November 2024, Beijing, China, pp. 388\u2013392 (2024)","DOI":"10.1109\/ISCSLP63861.2024.10800573"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zheng, S., Wang, H., Cheng, L., Chen, Q.: Pushing the limits of self-supervised speaker verification using regularized distillation framework. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4\u201310 June 2023, Rhodes Island, Greece, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096915"},{"key":"23_CR14","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1016\/j.procs.2018.01.083","volume":"123","author":"AA Yakovenko","year":"2018","unstructured":"Yakovenko, A.A., Malykhina, G.F.: Bio-inspired approach for automatic speaker clustering using auditory modeling and self-organizing maps. Procedia Comput. Sci. 123, 547\u2013552 (2018)","journal-title":"Procedia Comput. Sci."},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Liu, B., Wang, H., Chen, Z., Wang, S., Qian, Y.: Self-knowledge distillation via feature enhancement for speaker verification. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 23\u201327 May 2022, Singapore, pp. 7542\u20137546 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746529"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Peng, Y., Kim, K., Wu, F., Sridhar, P., Watanabe,S.: Structured pruning of self-supervised pre-trained models for speech recognition and understanding. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4\u201310 June 2023, Rhodes Island, Greece, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095780"},{"key":"23_CR17","doi-asserted-by":"publisher","first-page":"3771","DOI":"10.1109\/TASLP.2024.3437237","volume":"32","author":"B Liu","year":"2024","unstructured":"Liu, B., Wang, H., Qian, Y.: Towards lightweight speaker verification via adaptive neural network quantization. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 3771\u20133784 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"23_CR18","unstructured":"Li, J., Liu, W., Zhang, Z., Wang, J., Lee, T.: Model compression for DNN-based speaker verification using weight quantization. https:\/\/arxiv.org\/abs\/2210.17326. Accessed 27 June 2025"},{"key":"23_CR19","unstructured":"Iandola, F., Han, S., Moskewicz, M., Ashraf, K., Dally, W., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<$$0.5 mb model size (2016). https:\/\/arxiv.org\/abs\/1602.07360. Accessed 27 June 2025"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetV3. In IEEE\/CVF International Conference on Computer Vision (ICCV), 27 October\u20132 November 2019, Seoul, Korea (South), pp. 1314\u20141324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Warohma, A. M., Hindersah, H., Lestari, D. P.: Speaker recognition using MobileNetV3 for voice-based robot navigation. In: 11th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA), 28\u201330 September 2024, Singapore, pp. 1\u20136 (2024)","DOI":"10.1109\/ICAICTA63815.2024.10763225"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Meng, L., Xu, J., Tan, X., Wang, J., Qin, T., Xu, B.: MixSpeech: data augmentation for low-resource automatic speech recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 6\u201311 June 2021, Toronto, Ontario, Canada, pp. 7008\u20147012 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414483"},{"key":"23_CR23","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. https:\/\/arxiv.org\/abs\/1912.06670. Accessed 27 June 2025"},{"key":"23_CR24","unstructured":"He, R., et al.: On the effectiveness of adapter-based tuning for pretrained language model adaptation. https:\/\/arxiv.org\/abs\/2106.03164. Accessed 27 June 2025"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Xin, D., Saito, Y., Takamichi, S., Koriyama, T., Saruwatari, H.: Cross-lingual speaker adaptation using domain adaptation and speaker consistency loss for text-to-speech synthesis. In: Proceedings of the Interspeech 2021, 30 August\u20133 September 2021, Brno, Czechia, pp. 1614\u20141618 (2021)","DOI":"10.21437\/Interspeech.2021-897"},{"issue":"3","key":"23_CR26","doi-asserted-by":"publisher","first-page":"1912","DOI":"10.1109\/TAFFC.2022.3167013","volume":"14","author":"S Latif","year":"2023","unstructured":"Latif, S., Rana, R., Khalifa, S., Jurdak, R., Schuller, B.: Self-supervised adversarial domain adaptation for cross-corpus and cross-language speech emotion recognition. IEEE Trans. Affect. Comput. 14(3), 1912\u20131926 (2023)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Pang, J.: Spectrum energy based voice activity detection. In: 2017 IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC), 9\u201311 January 2017, Las Vegas, NV, USA, pp. 1\u20135 (2017)","DOI":"10.1109\/CCWC.2017.7868454"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:31Z","timestamp":1760253571000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","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":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}