{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T23:15:41Z","timestamp":1788390941640,"version":"build-2803163510"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":92,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"JHU+Amazon ai2ai faculty award","award":["No grant number"],"award-info":[{"award-number":["No grant number"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-026-07497-5","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T04:36:08Z","timestamp":1780461368000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HeyJay! A corpus of atypical speech for spoken language understanding and automatic speech recognition"],"prefix":"10.1038","volume":"13","author":[{"given":"Laureano","family":"Moro-Velazquez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alison","family":"Gunzler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milind","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur A.","family":"Butala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lora","family":"Clawson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Venkatesh","family":"Ravichandran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"7497_CR1","unstructured":"Jefferson, M. Usability of automatic speech recognition systems for individuals with speech disorders: Past, present, future, and a proposed model (2019)."},{"key":"7497_CR2","doi-asserted-by":"publisher","first-page":"e23006","DOI":"10.2196\/23006","volume":"8","author":"O Duffy","year":"2021","unstructured":"Duffy, O., Synnott, J., McNaney, R., Brito Zambrano, P. & Kernohan, W. G. Attitudes toward the use of voice-assisted technologies among people with parkinson disease: Findings from a web-based survey. JMIR Rehabil Assist Technol 8, e23006, https:\/\/doi.org\/10.2196\/23006 (2021).","journal-title":"JMIR Rehabil Assist Technol"},{"key":"7497_CR3","doi-asserted-by":"publisher","first-page":"e32161","DOI":"10.2196\/32161","volume":"23","author":"C B\u00e9rub\u00e9","year":"2021","unstructured":"B\u00e9rub\u00e9, C., Kovacs, Z. F., Fleisch, E. & Kowatsch, T. Reliability of commercial voice assistants\u2019 responses to health-related questions in noncommunicable disease management: Factorial experiment assessing response rate and source of information. J Med Internet Res 23, e32161, https:\/\/doi.org\/10.2196\/32161 (2021).","journal-title":"J Med Internet Res"},{"key":"7497_CR4","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1080\/02699052.2020.1763462","volume":"34","author":"GE Lancioni","year":"2020","unstructured":"Lancioni, G. E. et al. Mainstream technology to support basic communication and leisure in people with neurological disorders, motor impairment and lack of speech. Brain Injury 34, 921\u2013927, https:\/\/doi.org\/10.1080\/02699052.2020.1763462 (2020).","journal-title":"Brain Injury"},{"key":"7497_CR5","doi-asserted-by":"crossref","unstructured":"Martinez-Martin, E. & del Pobil, A. P. Personal robot assistants for elderly care: An overview. In Personal Assistants: Emerging Computational Technologies, 77\u201391 (Springer, New York, 2017).","DOI":"10.1007\/978-3-319-62530-0_5"},{"key":"7497_CR6","doi-asserted-by":"publisher","unstructured":"Awada, I. A., Mocanu, I., Florea, A. M. & Cramariuc, B. Multimodal interface for elderly people. In 2017 21st International Conference on Control Systems and Computer Science (CSCS), 536\u2013541 https:\/\/doi.org\/10.1109\/CSCS.2017.82 (2017).","DOI":"10.1109\/CSCS.2017.82"},{"key":"7497_CR7","doi-asserted-by":"crossref","unstructured":"Serdyuk, D. et al. Towards end-to-end spoken language understanding. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5754\u20135758 (IEEE, 2018).","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"7497_CR8","unstructured":"Yue, Z.Continuous speech recognition for people with dysarthria. Ph.D. thesis, (2022)."},{"key":"7497_CR9","doi-asserted-by":"crossref","unstructured":"Moro-Velazquez, L. et al. Study of the Performance of Automatic Speech Recognition Systems in Speakers with Parkinson\u2019s Disease. Proc. Interspeech, 3875-3879 (2019).","DOI":"10.21437\/Interspeech.2019-2993"},{"key":"7497_CR10","doi-asserted-by":"crossref","unstructured":"Evangeline, S. B. & Moorthy, A. D. Investigating ai applications in communication tools for individuals with speech impairments: An in-depth analysis. In 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), vol. 2, 1\u20136 (IEEE, 2024).","DOI":"10.1109\/IATMSI60426.2024.10502623"},{"key":"7497_CR11","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1109\/TASLP.2023.3323888","volume":"32","author":"Z Jin","year":"2023","unstructured":"Jin, Z. et al. Personalized adversarial data augmentation for dysarthric and elderly speech recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 32, 413\u2013429 (2023).","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"7497_CR12","doi-asserted-by":"publisher","first-page":"109954","DOI":"10.1016\/j.compbiomed.2025.109954","volume":"189","author":"C Bhat","year":"2025","unstructured":"Bhat, C. & Strik, H. Two-stage data augmentation for improved asr performance for dysarthric speech. Computers in Biology and Medicine 189, 109954 (2025).","journal-title":"Computers in Biology and Medicine"},{"key":"7497_CR13","doi-asserted-by":"publisher","unstructured":"Illa, M., Halpern, B. M., van Son, R., Moro-Vel\u00e1zquez, L. & Scharenborg, O. Pathological voice adaptation with autoencoder-based voice conversion. In Proc. ISCA Speech Synthesis Workshop 19\u201324 https:\/\/doi.org\/10.21437\/SSW.2021-4 (2021).","DOI":"10.21437\/SSW.2021-4"},{"key":"7497_CR14","doi-asserted-by":"publisher","first-page":"4278","DOI":"10.3390\/electronics12204278","volume":"12","author":"Z Qian","year":"2023","unstructured":"Qian, Z. & Xiao, K. A survey of automatic speech recognition for dysarthric speech. Electronics 12, 4278 (2023).","journal-title":"Electronics"},{"key":"7497_CR15","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.dhjo.2015.07.004","volume":"9","author":"MA Morris","year":"2016","unstructured":"Morris, M. A., Meier, S. K., Griffin, J. M., Branda, M. E. & Phelan, S. M. Prevalence and etiologies of adult communication disabilities in the united states: Results from the 2012 national health interview survey. Disability and health journal 9, 140\u2013144 (2016).","journal-title":"Disability and health journal"},{"key":"7497_CR16","doi-asserted-by":"publisher","first-page":"2359","DOI":"10.1002\/lary.24740","volume":"124","author":"N Bhattacharyya","year":"2014","unstructured":"Bhattacharyya, N. The prevalence of voice problems among adults in the united states. The Laryngoscope 124, 2359\u20132362 (2014).","journal-title":"The Laryngoscope"},{"key":"7497_CR17","doi-asserted-by":"crossref","unstructured":"Howarth, E., Vabulas, G., Connolly, S., Green, D. & Smolley, S. Developing accessible speech technology with users with dysarthric speech (2024).","DOI":"10.1080\/10400435.2024.2328082"},{"key":"7497_CR18","doi-asserted-by":"crossref","unstructured":"Gray, J. On a mission to help people sound like themselves: Rupal patel and her company vocalid build personalized voices by blending crowdsourced samples. The ASHA Leader Archive (2019).","DOI":"10.1044\/leader.LML.24072019.28"},{"key":"7497_CR19","doi-asserted-by":"crossref","unstructured":"Kim, H. et al. Dysarthric speech database for universal access research. Proc. Interspeech, 1741\u20131744 (2008).","DOI":"10.21437\/Interspeech.2008-480"},{"key":"7497_CR20","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. Language Resources and Evaluation 46, 523\u2013541 (2012).","journal-title":"Language Resources and Evaluation"},{"key":"7497_CR21","unstructured":"Garofolo, J. S. et al. TIMIT acoustic-phonetic continuous speech corpus. Tech. Rep. LDC93S1, Linguistic Data Consortium (1993)."},{"key":"7497_CR22","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. et al. Community-supported shared infrastructure in support of speech accessibility. Journal of Speech, Language, and Hearing Research 67, 4162\u20134175, https:\/\/doi.org\/10.1044\/2024_JSLHR-24-00122 (2024).","journal-title":"Journal of Speech, Language, and Hearing Research"},{"key":"7497_CR23","doi-asserted-by":"crossref","unstructured":"Wang, P. & hamme, H. V. Bottleneck low-rank transformers for low-resource spoken language understanding. In Ko, H. & Hansen, J. H. L. (eds.) Proc. Interspeech, 1248\u20131252 (ISCA, 2022).","DOI":"10.21437\/Interspeech.2022-10801"},{"key":"7497_CR24","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.3390\/electronics13071389","volume":"13","author":"D Mulfari","year":"2024","unstructured":"Mulfari, D. & Villari, M. A voice user interface on the edge for people with speech impairments. Electronics 13, 1389 (2024).","journal-title":"Electronics"},{"key":"7497_CR25","doi-asserted-by":"crossref","unstructured":"MacDonald, R. L. et al. Disordered speech data collection: Lessons learned at 1 million utterances from project Euphonia. Proc. Interspeech, 4833\u20134837, (2021).","DOI":"10.21437\/Interspeech.2021-697"},{"key":"7497_CR26","unstructured":"Park, J.-W. et al. Hermespeech recorder: a new open-source web platform to record speech to the cloud. In Proceedings of MAVEBA (2023)."},{"key":"7497_CR27","doi-asserted-by":"crossref","unstructured":"Lugosch, L., Ravanelli, M., Ignoto, P., Tomar, V. S. & Bengio, Y. Speech model pre-training for end-to-end spoken language understanding. Proc. Interspeech 2019 814\u2013818 (2019).","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"7497_CR28","doi-asserted-by":"crossref","unstructured":"Bastianelli, E., Vanzo, A., Swietojanski, P. & Rieser, V. SLURP: A spoken language understanding resource package. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 7252\u20137262 (Association for Computational Linguistics, 2020).","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"7497_CR29","unstructured":"Duffy, J.Motor Speech Disorders (Elsevier, Edinburgh, 2019), 4 edn."},{"key":"7497_CR30","doi-asserted-by":"publisher","unstructured":"Moro-Velazquez, L. et al. Heyjay!: A corpus of atypical speech for spoken language understanding and automatic speech recognition, united states, 2023-2024. Inter-university Consortium for Political and Social Research (ICPSR) https:\/\/doi.org\/10.3886\/ICPSR39448 (2025).","DOI":"10.3886\/ICPSR39448"},{"key":"7497_CR31","unstructured":"Radford, A. et al. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning, 28492\u201328518 (PMLR, 2023)."},{"key":"7497_CR32","unstructured":"Amorese, T. et al. Automatic speech recognition (asr) with whisper: Testing performances in different languages. In S3C@ CHItaly, 1\u20138 (2023)."},{"key":"7497_CR33","unstructured":"Zhang, Q. et al. Adaptive budget allocation for parameter-efficient fine-tuning. In The Eleventh International Conference on Learning Representations (2023)."},{"key":"7497_CR34","unstructured":"Wang, H. et al. Improving fairness for spoken language understanding in atypical speech with text-to-speech. In NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI (2023)."},{"key":"7497_CR35","doi-asserted-by":"crossref","unstructured":"Park, D. S. et al. Specaugment: A simple data augmentation method for automatic speech recognition. Proc. Interspeech 2613\u20132617 (2019).","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"7497_CR36","doi-asserted-by":"crossref","unstructured":"Kharitonov, E. et al. Data augmenting contrastive learning of speech representations in the time domain. In IEEE Spoken Language Technology Workshop (SLT), 215\u2013222 (2021).","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"7497_CR37","unstructured":"Popov, V., Vovk, I., Gogoryan, V., Sadekova, T. & Kudinov, M. Grad-tts: A diffusion probabilistic model for text-to-speech. In International Conference on Machine Learning, 8599\u20138608 (PMLR, 2021)."},{"key":"7497_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H. et al. Duta-vc: A duration-aware typical-to-atypical voice conversion approach with diffusion probabilistic model. In Proc. Interspeech 2023, 1548\u20131552 (2023).","DOI":"10.21437\/Interspeech.2023-2203"},{"key":"7497_CR39","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W-N Hsu","year":"2021","unstructured":"Hsu, W.-N. et al. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 29, 3451\u20133460 (2021).","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"7497_CR40","doi-asserted-by":"crossref","unstructured":"Lugosch, L., Meyer, B. H., Nowrouzezahrai, D. & Ravanelli, M. Using speech synthesis to train end-to-end spoken language understanding models. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 8499\u20138503 (IEEE, 2020).","DOI":"10.1109\/ICASSP40776.2020.9053063"},{"key":"7497_CR41","unstructured":"Yang, S. W. et al. Superb: Speech processing universal performance benchmark. In Proc. INTERSPEECH, 3161\u20133165 (2021)."},{"key":"7497_CR42","doi-asserted-by":"crossref","unstructured":"Arora, S. et al. Espnet-slu: Advancing spoken language understanding through espnet. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7167\u20137171 (IEEE, 2022).","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"7497_CR43","unstructured":"Peng, Y., Dalmia, S., Lane, I. & Watanabe, S. Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding. In International Conference on Machine Learning, 17627\u201317643 (PMLR, 2022)."},{"key":"7497_CR44","unstructured":"Ravanelli, M. et al. SpeechBrain: A general-purpose speech toolkit. ArXiv:2106.04624, 2106.04624. (2021)"}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07497-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07497-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07497-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T22:32:25Z","timestamp":1788388345000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07497-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,3]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["7497"],"URL":"https:\/\/doi.org\/10.1038\/s41597-026-07497-5","relation":{},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,3]]},"assertion":[{"value":"27 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"1267"}}