{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:23:02Z","timestamp":1760314982057,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079589","type":"print"},{"value":"9783032079596","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\/978-3-032-07959-6_10","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T09:22:06Z","timestamp":1760260926000},"page":"130-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain Knowledge and\u00a0Language Embeddings for\u00a0Low-Resource Multilingual Phoneme ASR"],"prefix":"10.1007","author":[{"given":"Anton","family":"Legchenko","sequence":"first","affiliation":[]},{"given":"Ivan","family":"Bondarenko","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"10_CR1","unstructured":"eSpeak NG: Open source speech synthesizer (2025). https:\/\/github.com\/espeak-ng\/espeak-ng"},{"key":"10_CR2","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670 (2019)"},{"key":"10_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020)"},{"issue":"10\u201311","key":"10_CR4","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1016\/j.specom.2007.02.006","volume":"49","author":"M Benzeghiba","year":"2007","unstructured":"Benzeghiba, M., et al.: Automatic speech recognition and speech variability: a review. Speech Commun. 49(10\u201311), 763\u2013786 (2007)","journal-title":"Speech Commun."},{"key":"10_CR5","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.specom.2013.07.008","volume":"56","author":"L Besacier","year":"2014","unstructured":"Besacier, L., Barnard, E., Karpov, A., Schultz, T.: Automatic speech recognition for under-resourced languages: a survey. Speech Commun. 56, 85\u2013100 (2014)","journal-title":"Speech Commun."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, S., Liu, Z., Li, L., Tang, Z., Wang, D., Zheng, T.F.: ASR-free pronunciation assessment. arXiv preprint arXiv:2005.11902 (2020)","DOI":"10.21437\/Interspeech.2020-2623"},{"key":"10_CR7","unstructured":"Collobert, R., Puhrsch, C., Synnaeve, G.: Wav2letter: an end-to-end convnet-based speech recognition system. arXiv preprint arXiv:1609.03193 (2016)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135888. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"10_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","volume-title":"Similarity-Based Pattern Recognition","author":"E Hoffer","year":"2015","unstructured":"Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 84\u201392. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24261-3_7"},{"key":"10_CR12","unstructured":"Kingma, D.P.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Li, B., Li, J., Zhao, R., Wang, Y., Gong, Y., Acero, A.: Universal phone recognition with a multilingual allophone system. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8249\u20138253. IEEE (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053564","DOI":"10.1109\/ICASSP40776.2020.9053564"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y.A., Han, C., Jiang, X., Mesgarani, N.: Phoneme-level BERT for enhanced prosody of text-to-speech with grapheme predictions. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10097074"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Lux, F., Vu, N.T.: Language-agnostic meta-learning for low-resource text-to-speech with articulatory features. arXiv preprint arXiv:2203.03191 (2022)","DOI":"10.18653\/v1\/2022.acl-long.472"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J.: Umap: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)","DOI":"10.21105\/joss.00861"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., Metze, F.: Eesen: end-to-end speech recognition using deep RNN models and WFST-based decoding. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 167\u2013174. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"10_CR18","unstructured":"Mortensen, D.R., Littell, P., Bharadwaj, A., Goyal, K., Dyer, C., Levin, L.: Panphon: a resource for mapping IPA segments to articulatory feature vectors. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 3475\u20133484 (2016)"},{"key":"10_CR19","unstructured":"Novak, J.R., Minematsu, N., Hirose, K.: WFST-based grapheme-to-phoneme conversion: open source tools for alignment, model-building and decoding. In: Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing, pp. 45\u201349 (2012)"},{"issue":"2","key":"10_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103148","volume":"60","author":"K Nowakowski","year":"2023","unstructured":"Nowakowski, K., Ptaszynski, M., Murasaki, K., Nieuwa\u017cny, J.: Adapting multilingual speech representation model for a new, underresourced language through multilingual fine-tuning and continued pretraining. Inf. Process. Manag. 60(2), 103148 (2023)","journal-title":"Inf. Process. Manag."},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. In: Readings in Speech Recognition, pp. 267\u2013296 (1990)","DOI":"10.1016\/B978-0-08-051584-7.50027-9"},{"key":"10_CR22","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Sanabria, R., Metze, F.: Hierarchical multitask learning with CTC. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 485\u2013490 (2018). https:\/\/api.semanticscholar.org\/CorpusID:61807503","DOI":"10.1109\/SLT.2018.8639530"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Sanh, V., Wolf, T., Ruder, S.: A hierarchical multi-task approach for learning embeddings from semantic tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 6949\u20136956 (2019)","DOI":"10.1609\/aaai.v33i01.33016949"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Sigtia, S., Marchi, E., Kajarekar, S., Naik, D., Bridle, J.: Multi-task learning for speaker verification and voice trigger detection. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6844\u20136848. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054760"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Smith, L.N.: Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 464\u2013472. IEEE (2017)","DOI":"10.1109\/WACV.2017.58"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., McCree, A., Povey, D., Khudanpur, S.: Speaker recognition for multi-speaker conversations using x-vectors. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5796\u20135800. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Toshniwal, S., et al.: Multilingual speech recognition with a single end-to-end model. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4904\u20134908. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"10_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30, no. 1, pp. 261\u2013272 (2017)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Q., Baevski, A., Auli, M.: Simple and effective zero-shot cross-lingual phoneme recognition. arXiv preprint arXiv:2109.11680 (2021)","DOI":"10.21437\/Interspeech.2022-60"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Yen, H.T., Wu, W.C., Chang, S.H., Tsao, Y., Wang, H.M., Hsieh, T.H.: Boosting end-to-end multilingual phoneme recognition through exploiting universal speech attributes constraints. arXiv preprint arXiv:2309.08828 (2023)","DOI":"10.1109\/ICASSP48485.2024.10447568"},{"issue":"12","key":"10_CR32","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","volume":"34","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. IEEE Trans. Knowl. Data Eng. 34(12), 5586\u20135609 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07959-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T09:22:18Z","timestamp":1760260938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07959-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079589","9783032079596"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07959-6_10","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":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"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"}}]}}