{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T08:41:09Z","timestamp":1760258469999,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032079558"},{"type":"electronic","value":"9783032079565"}],"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_14","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:27Z","timestamp":1760253567000},"page":"203-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-to-Dysarthric-Speech Generation for\u00a0Dysarthric Automatic Speech Recognition: Is Purely Synthetic Data Enough?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4888-1951","authenticated-orcid":false,"given":"Wing-Zin","family":"Leung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3028-5062","authenticated-orcid":false,"given":"Heidi","family":"Christensen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1044-7343","authenticated-orcid":false,"given":"Stefan","family":"Goetze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Cadet, X.F., Aloufi, R., Ahmadi-Abhari, S., Haddadi, H.: A study on the impact of self-supervised learning on automatic dysarthric speech assessment. In: ICASSP Workshops (ICASSPW) (2024)","DOI":"10.1109\/ICASSPW62465.2024.10626129"},{"issue":"1","key":"14_CR2","first-page":"17","volume":"2","author":"AN Chadha","year":"2014","unstructured":"Chadha, A.N., Nirmal, J.H., Kachare, P.: A comparative performance of various speech analysis-synthesis techniques. Int. J. Signal Process. Syst. 2(1), 17\u201322 (2014)","journal-title":"Int. J. Signal Process. Syst."},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Christensen, H., Casanueva, I., Cunningham, S., Green, P., Hain, T.: Automatic selection of speakers for improved acoustic modelling: recognition of disordered speech with sparse data. In: 2014 IEEE Spoken Language Technology Workshop (SLT), pp. 254\u2013259. IEEE (2014)","DOI":"10.1109\/SLT.2014.7078583"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Churchwell, C., Morrison, M., Pardo, B.: High-fidelity neural phonetic posteriorgrams. arXiv preprint arXiv:2402.17735 (2024)","DOI":"10.1109\/ICASSPW62465.2024.10669905"},{"issue":"2","key":"14_CR5","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1080\/07434618.2023.2206910","volume":"39","author":"ZC Clarke","year":"2023","unstructured":"Clarke, Z.C., Judge, S., Fryer, K., Cunningham, S., Toogood, J., Hawley, M.S.: A qualitative study exploring the effect of communicating with partially intelligible speech. Augment. Altern. Commun. 39(2), 110\u2013122 (2023)","journal-title":"Augment. Altern. Commun."},{"key":"14_CR6","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR7","unstructured":"Duffy, J.R.: Motor Speech Disorders. Elsevier (2019)"},{"key":"14_CR8","unstructured":"Enderby, P.: Frenchay Dysarthria Assessment. Pro-Ed (1983)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Espana-Bonet, C., Fonollosa, J.A.: Automatic speech recognition with deep neural networks for impaired speech. In: IberSPEECH (2016)","DOI":"10.1007\/978-3-319-49169-1_10"},{"key":"14_CR10","unstructured":"Geng, M., et al.: Investigation of data augmentation techniques for disordered speech recognition. arXiv preprint arXiv:2201.05562 (2022)"},{"key":"14_CR11","doi-asserted-by":"publisher","DOI":"10.3109\/17538157.2010.528655","author":"S Goetze","year":"2010","unstructured":"Goetze, S., Moritz, N., Appell, J.E., Meis, M., Bartsch, C., Bitzer, J.: Acoustic user interfaces for ambient-assisted living technologies. Inform. Health Soc. Care (2010). https:\/\/doi.org\/10.3109\/17538157.2010.528655","journal-title":"Inform. Health Soc. Care"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Gosztolya, G., Svindt, V., B\u00f3na, J., Hoffmann, I.: Extracting phonetic posterior-based features for detecting multiple sclerosis from speech. IEEE Trans. Neural Syst. Rehabil. Eng. (2023)","DOI":"10.1109\/TNSRE.2023.3300532"},{"issue":"2","key":"14_CR13","doi-asserted-by":"publisher","first-page":"39","DOI":"10.7224\/1537-2073-6.2.39","volume":"6","author":"L Hartelius","year":"2004","unstructured":"Hartelius, L., et al.: How does fatigue affect communication? The influence of fatigue on cognitive, physical, psychosocial and communicative ability in individuals with multiple sclerosis. Int. J. MS Care 6(2), 39\u201351 (2004)","journal-title":"Int. J. MS Care"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Hazen, T.J., Shen, W., White, C.: Query-by-example spoken term detection using phonetic posteriorgram templates. In: ASRU (2009)","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"14_CR15","doi-asserted-by":"publisher","unstructured":"Hermann, E., Magimai-Doss, M.: Dysarthric speech recognition with lattice-free MMI. In: ICASSP (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053549","DOI":"10.1109\/ICASSP40776.2020.9053549"},{"issue":"3","key":"14_CR16","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1080\/07434610701571058","volume":"23","author":"DJ Higginbotham","year":"2007","unstructured":"Higginbotham, D.J., Shane, H., Russell, S., Caves, K.: Access to AAC: present, past, and future. Augment. Altern. Commun. 23(3), 243\u2013257 (2007). https:\/\/doi.org\/10.1080\/07434610701571058","journal-title":"Augment. Altern. Commun."},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Hu, S., et\u00a0al.: Self-supervised ASR models and features for dysarthric and elderly speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. (2024)","DOI":"10.1109\/TASLP.2024.3422839"},{"key":"14_CR18","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICC52391.2025.11161747"},{"key":"14_CR19","doi-asserted-by":"publisher","unstructured":"Janbakhshi, P., Kodrasi, I., Bourlard, H.: Pathological speech intelligibility assessment based on the short-time objective intelligibility measure. In: ICASSP (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683741","DOI":"10.1109\/ICASSP.2019.8683741"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Tu, M., Berisha, V., Liss, J.: Simulating dysarthric speech for training data augmentation in clinical speech applications. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018)","DOI":"10.1109\/ICASSP.2018.8462290"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Jin, Z., et al.: Personalized adversarial data augmentation for dysarthric and elderly speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. (2023)","DOI":"10.1109\/TASLP.2023.3323888"},{"key":"14_CR22","doi-asserted-by":"publisher","unstructured":"Jin, Z., et al.: Adversarial data augmentation for disordered speech recognition. In: Interspeech, pp. 4803\u20134807 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-168","DOI":"10.21437\/Interspeech.2021-168"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Kanda, N., Takeda, R., Obuchi, Y.: Elastic spectral distortion for low resource speech recognition with deep neural networks. In: ASRU (2013)","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Klopfenstein, M., Bernard, K., Heyman, C.: The study of speech naturalness in communication disorders: a systematic review of the literature. Clin. Linguist. Phonetics 34(4) (2020)","DOI":"10.1080\/02699206.2019.1652692"},{"key":"14_CR25","unstructured":"Kominek, J., Schultz, T., Black, A.W.: Synthesizer voice quality of new languages calibrated with mean mel cepstral distortion. In: SLTU, pp. 63\u201368 (2008)"},{"key":"14_CR26","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"14_CR27","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: Interspeech. Kos, Greece (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-1645","DOI":"10.21437\/Interspeech.2024-1645"},{"issue":"1","key":"14_CR28","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/18.61115","volume":"37","author":"J Lin","year":"1991","unstructured":"Lin, J.: Divergence measures based on the Shannon entropy. IEEE Trans. Inf. Theory 37(1), 145\u2013151 (1991)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"14_CR29","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Mehta, S., Tu, R., Beskow, J., Sz\u00e9kely, \u00c9., Henter, G.E.: Matcha-TTS: a fast TTS architecture with conditional flow matching. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2024)","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Mehta, S., Wang, S., Alexanderson, S., Beskow, J., Sz\u00e9kely, \u00c9., Henter, G.E.: Diff-TTSG: denoising probabilistic integrated speech and gesture synthesis. arXiv preprint arXiv:2306.09417 (2023)","DOI":"10.21437\/SSW.2023-24"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Mujtaba, D., Mahapatra, N.R., Arney, M., Yaruss, J.S., Herring, C., Bin, J.: Inclusive ASR for disfluent speech: cascaded large-scale self-supervised learning with targeted fine-tuning and data augmentation. arXiv preprint arXiv:2406.10177 (2024)","DOI":"10.21437\/Interspeech.2024-2246"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Newberry, A., et al.: Understanding recruitment and retention in neurological research. J. Neurosci. Nurs. 42(1) (2010)","DOI":"10.1097\/JNN.0b013e3181c1fdd9"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"14_CR35","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 (2021)"},{"key":"14_CR36","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 (2023)"},{"issue":"4","key":"14_CR37","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s10579-011-9145-0","volume":"46","author":"F Rudzicz","year":"2011","unstructured":"Rudzicz, F., Namasivayam, A.K., Wolff, T.: The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang. Resour. Eval. 46(4), 523\u2013541 (2011). https:\/\/doi.org\/10.1007\/s10579-011-9145-0","journal-title":"Lang. Resour. Eval."},{"issue":"3","key":"14_CR38","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1016\/j.specom.2011.10.006","volume":"54","author":"F Rudzicz","year":"2012","unstructured":"Rudzicz, F.: Using articulatory likelihoods in the recognition of dysarthric speech. Speech Commun. 54(3), 430\u2013444 (2012)","journal-title":"Speech Commun."},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Shahamiri, S.R.: Speech vision: an end-to-end deep learning-based dysarthric automatic speech recognition system. IEEE Trans. Neural Syst. Rehabil. Eng. 29 (2021)","DOI":"10.1109\/TNSRE.2021.3076778"},{"issue":"3","key":"14_CR40","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379\u2013423 (1948)","journal-title":"Bell Syst. Tech. J."},{"key":"14_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103112","volume":"164","author":"M Soleymanpour","year":"2024","unstructured":"Soleymanpour, M., Johnson, M.T., Soleymanpour, R., Berry, J.: Accurate synthesis of dysarthric speech for ASR data augmentation. Speech Commun. 164, 103112 (2024)","journal-title":"Speech Commun."},{"key":"14_CR42","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International\u00a0Conference\u00a0on Learning Representations (2021)"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Takashima, R., Takiguchi, T., Ariki, Y.: Two-step acoustic model adaptation for dysarthric speech recognition. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053725"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Van\u00a0Nuffelen, G., Middag, C., De\u00a0Bodt, M., Martens, J.P.: Speech technology-based assessment of phoneme intelligibility in dysarthria. Int. J. Lang. Commun. Disorders (2009)","DOI":"10.1080\/13682820802342062"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Wang, C.C., Ling, Z.H., Zhang, B.F., Dai, L.R.: Multi-layer F0 modeling for HMM-based speech synthesis. In: 2008 6th International Symposium on Chinese Spoken Language Processing. IEEE (2008)","DOI":"10.1109\/CHINSL.2008.ECP.44"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Duta-VC: a duration-aware typical-to-atypical voice conversion approach with diffusion probabilistic model. arXiv preprint arXiv:2306.10588 (2023)","DOI":"10.21437\/Interspeech.2023-2203"},{"key":"14_CR47","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Enhancing pre-trained ASR system fine-tuning for dysarthric speech recognition using adversarial data augmentation. In: ICASSP (2024)","DOI":"10.1109\/ICASSP48485.2024.10447702"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Xiong, F., Barker, J., Yue, Z., Christensen, H.: Source domain data selection for improved transfer learning targeting dysarthric speech recognition. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"14_CR49","doi-asserted-by":"publisher","unstructured":"Yue, Z., Xiong, F., Christensen, H., Barker, J.: Exploring appropriate acoustic and language modelling choices for continuous dysarthric speech recognition. In: ICASSP 2020 (2020). https:\/\/doi.org\/10.1109\/icassp40776.2020.9054343","DOI":"10.1109\/icassp40776.2020.9054343"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Yusufali, H., Moore, R.K., Goetze, S.: Refining text input for augmentative and alternative communication (AAC) devices: analysing language model layers for optimisation. In: ICASSP 2024 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446094"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Zen, H., et al.: Libritts: a corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882 (2019)","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"Zheng, W.Z., Han, J.Y., Cheng, H.L., Chu, W.C., Chen, K.C., Lai, Y.H.: Comparing the performance of classic voice-driven assistive systems for dysarthric speech. Biomedical Sig. Proc. and Control (2023)","DOI":"10.1016\/j.bspc.2022.104447"}],"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_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T08:02:24Z","timestamp":1760256144000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}