{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:47:21Z","timestamp":1776883641447,"version":"3.51.2"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032025500","type":"print"},{"value":"9783032025517","type":"electronic"}],"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\/978-3-032-02551-7_14","type":"book-chapter","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T05:27:28Z","timestamp":1755754048000},"page":"153-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing ASR Accuracy for\u00a0Speakers with\u00a0Parkinson\u2019s Disease Using Instruction-Tuned LLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7001-6767","authenticated-orcid":false,"given":"Abner","family":"Hernandez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9405-4154","authenticated-orcid":false,"given":"Tom\u00e1s","family":"Arias-Vergara","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9550-5284","authenticated-orcid":false,"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2727-2116","authenticated-orcid":false,"given":"Paula\u00a0Andrea","family":"P\u00e9rez-Toro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Attaluri, K., CHVS, A., Chittepu, S.: Empowering dysarthric speech: leveraging advanced LLMs for accurate speech correction and multimodal emotion analysis. arXiv preprint arXiv:2410.12867 (2024)","DOI":"10.32388\/Q35C4V"},{"key":"14_CR2","doi-asserted-by":"publisher","unstructured":"Bowman, S.R., Angeli, G., Potts, C., et al.: A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 632\u2013642. Association for Computational Linguistics, Lisbon, Portugal (2015). https:\/\/doi.org\/10.18653\/v1\/D15-1075","DOI":"10.18653\/v1\/D15-1075"},{"key":"14_CR3","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1162\/tacl_a_00576","volume":"11","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Eger, S.: MENLI: robust evaluation metrics from natural language inference. Trans. Assoc. Comput. Linguist. 11, 804\u2013825 (2023). https:\/\/doi.org\/10.1162\/tacl_a_00576","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"14_CR4","unstructured":"Choi, D.L., Kim, B.W., Kim, Y.W., et al.: Dysarthric speech database for development of QoLT software technology. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC 2012), pp. 3378\u20133381. European Language Resources Association (ELRA), Istanbul, Turkey (2012)"},{"issue":"2","key":"14_CR5","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1044\/jshr.1202.246","volume":"12","author":"FL Darley","year":"1969","unstructured":"Darley, F.L., Aronson, A.E., Brown, J.R.: Differential diagnostic patterns of dysarthria. J. Speech Hear. Res. 12(2), 246\u2013269 (1969). https:\/\/doi.org\/10.1044\/jshr.1202.246","journal-title":"J. Speech Hear. Res."},{"key":"14_CR6","unstructured":"Duffy, J.R.: Motor Speech Disorders: Substrates, Differential Diagnosis, and Management, 4th edn. Elsevier, St. Louis (2020)"},{"key":"14_CR7","doi-asserted-by":"publisher","unstructured":"Guo, J., Sainath, T.N., Weiss, R.J.: A spelling correction model for end-to-end speech recognition. In: ICASSP 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5651\u20135655 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683745","DOI":"10.1109\/ICASSP.2019.8683745"},{"issue":"11","key":"14_CR8","doi-asserted-by":"publisher","first-page":"4162","DOI":"10.1044\/2024_JSLHR-24-00122","volume":"67","author":"M Hasegawa-Johnson","year":"2024","unstructured":"Hasegawa-Johnson, M., Zheng, X., Kim, H., et al.: Community-supported shared infrastructure in support of speech accessibility. J. Speech Lang. Hear. Res. 67(11), 4162\u20134175 (2024). https:\/\/doi.org\/10.1044\/2024_JSLHR-24-00122","journal-title":"J. Speech Lang. Hear. Res."},{"key":"14_CR9","doi-asserted-by":"publisher","unstructured":"Hernandez, A., P\u00e9rez-Toro, P.A., Noeth, E., et al.: Cross-lingual self-supervised speech representations for improved dysarthric speech recognition. In: Interspeech 2022, pp. 51\u201355 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10674","DOI":"10.21437\/Interspeech.2022-10674"},{"key":"14_CR10","doi-asserted-by":"publisher","unstructured":"Hrinchuk, O., Popova, M., Ginsburg, B.: Correction of automatic speech recognition with transformer sequence-to-sequence model. In: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7074\u20137078 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053051","DOI":"10.1109\/ICASSP40776.2020.9053051"},{"key":"14_CR11","unstructured":"Hu, E.J., Shen, Y., Wallis, P., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"14_CR12","unstructured":"Hui, M., Zhang, J., Mohan, A.: Enhancing AAC software for dysarthric speakers in e-health settings: an evaluation using torgo. arXiv preprint arXiv:2411.00980 (2024)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Kim, H., Hasegawa-Johnson, M., Perlman, A., et al.: Dysarthric speech database for universal access research. In: Interspeech, vol.\u00a02008, pp. 1741\u20131744 (2008)","DOI":"10.21437\/Interspeech.2008-480"},{"key":"14_CR14","unstructured":"Li, C.J., Yeo, E., Choi, K., et al.: Towards inclusive ASR: investigating voice conversion for dysarthric speech recognition in low-resource languages. arXiv preprint arXiv:2505.14874 (2025)"},{"key":"14_CR15","doi-asserted-by":"publisher","unstructured":"Li, S., Chen, C., Kwok, C.Y., et al.: Investigating ASR error correction with large language model and multilingual 1-best hypotheses. In: Interspeech 2024, pp. 1315\u20131319 (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-368","DOI":"10.21437\/Interspeech.2024-368"},{"key":"14_CR16","doi-asserted-by":"publisher","unstructured":"Ma, R., Gales, M.J.F., Knill, K.M., et al.: N-best t5: Robust ASR error correction using multiple input hypotheses and constrained decoding space. In: Interspeech 2023, pp. 3267\u20133271 (2023). https:\/\/doi.org\/10.21437\/Interspeech.2023-1616","DOI":"10.21437\/Interspeech.2023-1616"},{"key":"14_CR17","unstructured":"Ma, R., Qian, M., Manakul, P., et al.: Can generative large language models perform ASR error correction? arXiv preprint arXiv:2307.04172 (2023)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Nie, Y., Chen, H., Bansal, M.: Combining fact extraction and verification with neural semantic matching networks. In: Association for the Advancement of Artificial Intelligence (AAAI) (2019)","DOI":"10.1609\/aaai.v33i01.33016859"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Nie, Y., Williams, A., Dinan, E., et al.: Adversarial NLI: a new benchmark for natural language understanding. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.441"},{"key":"14_CR20","unstructured":"Orozco-Arroyave, J.R., Arias-Londo\u00f1o, J.D., Vargas-Bonilla, J.F., et al.: New Spanish speech corpus database for the analysis of people suffering from Parkinson\u2019s disease. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014), pp. 342\u2013347. European Language Resources Association (ELRA), Reykjavik, Iceland (2014)"},{"key":"14_CR21","doi-asserted-by":"publisher","unstructured":"Panayotov, V., Chen, G., Povey, D., et al.: 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). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"14_CR22","unstructured":"Radford, A., Kim, J.W., Xu, T., et al.: Robust speech recognition via large-scale weak supervision. In: Krause, A., Brunskill, E., Cho, K., et al. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 28492\u201328518. PMLR (2023)"},{"key":"14_CR23","doi-asserted-by":"publisher","unstructured":"Radhakrishnan, S., Yang, C.H., Khan, S., et al.: Whispering LLaMA: a cross-modal generative error correction framework for speech recognition. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 10007\u201310016. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.618","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"14_CR24","doi-asserted-by":"publisher","unstructured":"Rekesh, D., Koluguri, N.R., Kriman, S., et al.: Fast conformer with linearly scalable attention for efficient speech recognition. In: 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.\u00a01\u20138 (2023). https:\/\/doi.org\/10.1109\/ASRU57964.2023.10389701","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"14_CR25","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":"14_CR26","unstructured":"Srivastav, V., Majumdar, S., Koluguri, N., Moumen, A., Gandhi, S., et\u00a0al.: Open automatic speech recognition leaderboard (2023). https:\/\/huggingface.co\/spaces\/hf-audio\/open_asr_leaderboard"},{"key":"14_CR27","doi-asserted-by":"publisher","unstructured":"Turrisi, R., Braccia, A., Emanuele, M., et al.: Easycall corpus: a dysarthric speech dataset. In: Interspeech 2021, pp. 41\u201345 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-549","DOI":"10.21437\/Interspeech.2021-549"},{"key":"14_CR28","unstructured":"Wagner, D., Baumann, I., Engert, N., et al.: Personalized fine-tuning with controllable synthetic speech from LLM-generated transcripts for dysarthric speech recognition. arXiv preprint arXiv:2505.12991 (2025)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference. In: NAACL-HLT, pp. 1112\u20131122 (2018)","DOI":"10.18653\/v1\/N18-1101"},{"key":"14_CR30","unstructured":"Xu, H., Jia, F., Majumdar, S., et al.: Efficient sequence transduction by jointly predicting tokens and durations. In: International Conference on Machine Learning, pp. 38462\u201338484. PMLR (2023)"},{"key":"14_CR31","doi-asserted-by":"publisher","unstructured":"Yang, C.H.H., Gu, Y., Liu, Y.C., et al.: Generative speech recognition error correction with large language models and task-activating prompting. In: 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.\u00a01\u20138 (2023). https:\/\/doi.org\/10.1109\/ASRU57964.2023.10389673","DOI":"10.1109\/ASRU57964.2023.10389673"},{"key":"14_CR32","doi-asserted-by":"publisher","unstructured":"Yang, C.H.H., Park, T., Gong, Y., et al.: Large language model based generative error correction: a challenge and baselines for speech recognition, speaker tagging, and emotion recognition. In: 2024 IEEE Spoken Language Technology Workshop (SLT), pp. 371\u2013378 (2024). https:\/\/doi.org\/10.1109\/SLT61566.2024.10832176","DOI":"10.1109\/SLT61566.2024.10832176"},{"key":"14_CR33","unstructured":"Zhang, T., Kishore, V., Wu, F., et al.: Bertscore: evaluating text generation with BERT. In: International Conference on Learning Representations (2020)"}],"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\/978-3-032-02551-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T18:04:41Z","timestamp":1757441081000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02551-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"ISBN":["9783032025500","9783032025517"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02551-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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"}}]}}