{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:16:35Z","timestamp":1757625395705,"version":"3.44.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032025470"},{"type":"electronic","value":"9783032025487"}],"license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"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\/978-3-032-02548-7_16","type":"book-chapter","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:39:52Z","timestamp":1755754792000},"page":"182-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Synthesising Cross-Speaker Data for\u00a0Low-Resource Pathological Speech Recognition with\u00a0PEFT"],"prefix":"10.1007","author":[{"given":"Kesego","family":"Mokgosi","sequence":"first","affiliation":[]},{"given":"Milad","family":"Dadgar","sequence":"additional","affiliation":[]},{"given":"Cathy","family":"Ennis","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Ross","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","unstructured":"Ao, J., et al.: SpeechT5: unified-modal encoder-decoder pre-training for spoken language processing. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5723\u20135738. Association for Computational Linguistics, Dublin (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.393","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, C., Strik, H.: Speech technology for automatic recognition and assessment of dysarthric speech: an overview. J. Speech, Lang. Hear. Res. 1\u201331 (2025)","DOI":"10.54195\/9789465150314"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"Enderby, P.: Disorders of communication: dysarthria. 110, 273\u2013281 (2013). https:\/\/doi.org\/10.1016\/B978-0-444-52901-5.00022-8","DOI":"10.1016\/B978-0-444-52901-5.00022-8"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Feng, T., Dimitriadis, D., Narayanan, S.S.: Can synthetic audio from generative foundation models assist audio recognition and speech modeling? arXiv abs\/2406.08800 (2024)","DOI":"10.21437\/Interspeech.2024-1350"},{"key":"16_CR5","unstructured":"Gerz, D., et al.: Multilingual and cross-lingual intent detection from spoken data. CoRR abs\/2104.08524 (2021). https:\/\/arxiv.org\/abs\/2104.08524"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Hair, A., et al.: A longitudinal evaluation of tablet-based child speech therapy with apraxia world. ACM Trans. Accessible Comput. 14 (2021). https:\/\/doi.org\/10.1145\/3433607","DOI":"10.1145\/3433607"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Hermann, E., Doss, M.M.: Few-shot dysarthric speech recognition with text-to-speech data augmentation. In: Proc. INTERSPEECH 2023, pp. 156\u2013160 (2023)","DOI":"10.21437\/Interspeech.2023-2481"},{"key":"16_CR8","doi-asserted-by":"publisher","unstructured":"Hsieh, I.T., Wu, C.H.: Dysarthric speech recognition using curriculum learning and articulatory feature embedding. In: International Speech Communication Association, pp. 1300\u20131304 (2024). https:\/\/doi.org\/10.21437\/interspeech.2024-444","DOI":"10.21437\/interspeech.2024-444"},{"key":"16_CR9","unstructured":"Hu, E., et al.: Lora: low-rank adaptation of large language models. In: ICLR 2022 - 10th International Conference on Learning Representations. International Conference on Learning Representations, ICLR (2022)"},{"key":"16_CR10","unstructured":"Jefferson, M.: Usability of automatic speech recognition systems for individuals with speech disorders: Past, present, future, and a proposed model (2019)"},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Leivaditi, S., Matsushima, T., Coler, M., Nayak, S., Verkhodanova, V.: Fine-tuning strategies for dutch dysarthric speech recognition: evaluating the impact of healthy, disease-specific, and speaker-specific data. In: International Speech Communication Association, pp. 1295\u20131299 (2024). https:\/\/doi.org\/10.21437\/interspeech.2024-1231","DOI":"10.21437\/interspeech.2024-1231"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Leung, W.Z., Cross, M., Ragni, A., Goetze, S.: Training data augmentation for dysarthric automatic speech recognition by text-to-dysarthric-speech synthesis. In: International Speech Communication Association, pp. 2494\u20132498 (2024). https:\/\/doi.org\/10.21437\/interspeech.2024-1645","DOI":"10.21437\/interspeech.2024-1645"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"von Platen, P., Zhang, C., Woodland, P.: Multi-span acoustic modelling using raw waveform signals. arXiv preprint arXiv:1906.11047 (2019)","DOI":"10.21437\/Interspeech.2019-2454"},{"key":"16_CR14","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":"16_CR15","unstructured":"Ravanelli, M., et al.: Speechbrain: a general-purpose speech toolkit (2021)"},{"key":"16_CR16","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s10579-011-9145-0","volume":"46","author":"F Rudzicz","year":"2012","unstructured":"Rudzicz, F., Namasivayam, A.K., Wolff, T.: The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang. Resour. Eval. 46, 523\u2013541 (2012)","journal-title":"Lang. Resour. Eval."},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Silovsky, J., et al.: Cross-lingual knowledge transfer and iterative pseudo-labeling for low-resource speech recognition with transducers (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.13652","DOI":"10.48550\/arXiv.2305.13652"},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Thai, B., Jimerson, R., Arcoraci, D., Prud\u2019hommeaux, E., Ptucha, R.: Synthetic data augmentation for improving low-resource ASR. In: 2019 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2019. Institute of Electrical and Electronics Engineers Inc. (2019). https:\/\/doi.org\/10.1109\/WNYIPW.2019.8923082","DOI":"10.1109\/WNYIPW.2019.8923082"},{"key":"16_CR19","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online (2020). https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"issue":"6","key":"16_CR20","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1109\/TPAMI.2007.1078","volume":"29","author":"L Yujian","year":"2007","unstructured":"Yujian, L., Bo, L.: A normalized levenshtein distance metric. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1091\u20131095 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02548-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T18:05:22Z","timestamp":1757441122000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02548-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"ISBN":["9783032025470","9783032025487"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02548-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,22]]},"assertion":[{"value":"22 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Erlangen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.kiv.zcu.cz\/tsd2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}