{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T23:02:39Z","timestamp":1792364559520,"version":"4.4.0"},"reference-count":54,"publisher":"American Speech Language Hearing Association","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Speech Lang Hear Res"],"published-print":{"date-parts":[[2026,8,11]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose:<\/jats:title>\n                    <jats:p>This study investigated the intelligibility and processing characteristics of Mandarin sentences synthesized based on a large-scale language model (LLM), compared to natural speech, specifically for deaf adults with cochlear implants (CIs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method:<\/jats:title>\n                    <jats:p>Fifty participants, 25 Mandarin-speaking deaf adults with CIs and 25 Mandarin-speaking adults with normal hearing (NH), were enrolled in the study. Sentence recognition rates and reaction times were measured using sentences from the Mandarin speech perception database presented as six different speech types. These included original natural speech by a single female speaker at slow and normal speaking rates as well as synthetic speech generated by the LLM-based text-to-speech (TTS) model in two different voices (male and female) at two speaking rates (slow and normal). Linear mixed-effect models analyzed how sentence recognition accuracy and reaction time varied with listener group and speech type.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>Participants with CIs demonstrated significantly lower sentence recognition rates and longer reaction times than NH participants for both natural and synthetic speech. Participants with CIs exhibited greater individual variability than NH listeners in terms of sentence recognition performance and reaction times. Changes in speaking rate significantly impacted the recognition rates of participants with CIs. Crucially, when controlling for speaking rate differences, there was no significant difference in sentence recognition rates or reaction times between natural and LLM-based synthetic speech for participants with CIs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>The results suggest that LLM-based synthetic speech could achieve intelligibility levels indistinguishable from natural speech for CI recipients under comparable speaking rate conditions, similar to its performance for NH listeners. This study offers valuable insights for the future application of advanced TTS models in speech perception assessment and auditory rehabilitation for patients with CIs, including the potential development of personalized training materials.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplemental Material:<\/jats:title>\n                    <jats:p>\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/doi.org\/10.23641\/asha.32736135\">https:\/\/doi.org\/10.23641\/asha.32736135<\/jats:ext-link>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1044\/2026_jslhr-25-00295","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T22:13:24Z","timestamp":1782771204000},"page":"3977-3993","source":"Crossref","is-referenced-by-count":1,"title":["Perception of Synthesized Mandarin Speech Based on a Large-Scale Language Model Among Deaf Adults With Cochlear Implants"],"prefix":"10.1044","volume":"69","author":[{"given":"Ju","family":"Zhang","sequence":"first","affiliation":[{"name":"Technical College for the Deaf, Tianjin University of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Bai","sequence":"additional","affiliation":[{"name":"Technical College for the Deaf, Tianjin University of Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0557-4316","authenticated-orcid":false,"given":"Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Foreign Languages, Southeast University, Nanjing, China"},{"name":"National Research Center for Language and Well-being, Shanghai Jiao Tong University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1310","reference":[{"key":"e_1_3_2_2_1","unstructured":"Anastassiou P. Chen J. Chen J. Chen Y. Chen Z. Chen Z. Cong J. Deng L. Ding C. Gao L. Gong M. Huang P. Huang Q. Huang Z. Huo Y. Jia D. Li C. Li F. Li H. \u2026 Zhuang X. (2024). Seed-TTS: A family of high-quality versatile speech generation models. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2406.02430"},{"key":"e_1_3_2_3_1","unstructured":"Bates D. Machler M. Bolker B. & Walker S. (2014). Fitting linear mixed-effects models using lme4. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1406.5823"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoto.2020.0998"},{"key":"e_1_3_2_5_1","unstructured":"Bunnell H. T. (2010). Crafting small databases for unit selection TTS: Effects on intelligibility. In Proceedings of the ISCA Tutorial and Research Workshop on Speech Synthesis (SSW7) (pp. 40\u201344). https:\/\/www.isca-archive.org\/ssw_2010\/bunnell10_ssw.pdf [PDF]"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.3766\/jaaa.19002"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.1062582"},{"key":"e_1_3_2_8_1","first-page":"106","author":"Chen Y.","year":"2024","unstructured":"Chen, Y., Bu, Y., & Zhang, J. (2024). A study on the effectiveness of Mandarin seven-sound test across multiple speakers. In Proceedings of IEEE International Symposium on Chinese Spoken Language Processing (ISCSLP) (pp. 106\u2013110). https:\/\/doi.org\/10.1109\/ISCSLP63861.2024.10799998","journal-title":"Proceedings of IEEE International Symposium on Chinese Spoken Language Processing (ISCSLP)"},{"issue":"2","key":"e_1_3_2_9_1","first-page":"169","article-title":"Cochlear implantation: An overview","volume":"80","author":"Deep N. L.","year":"2018","unstructured":"Deep, N. L., Dowling, E. M., Jethanamest, D., & Carlson, M. L. (2018). Cochlear implantation: An overview. Journal of Neurological Surgery, 80(2), 169\u2013177. https:\/\/doi.org\/10.1055\/s-0038-1669411","journal-title":"Journal of Neurological Surgery"},{"key":"e_1_3_2_10_1","unstructured":"Eide E. Aaron A. Bakis R. Hamza W. Picheny M. & Pitrelli J. F. (2004). A corpus-based approach to expressive speech synthesis. In 5th ISCA Workshop on Speech Synthesis Pittsburgh PA (pp. 79\u201384). https:\/\/www.isca-archive.org\/ssw_2004\/eide04_ssw.html"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/07908318.2019.1662432"},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/deafed\/enx033"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.3590739"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-3900-4"},{"key":"e_1_3_2_15_1","first-page":"79","author":"Hu Y.-J.","year":"2017","unstructured":"Hu, Y.-J., Ding, C., Liu, L.-J., Ling, Z.-H, & Dai, L.-R. (2017). The USTC system for blizzard challenge 2017. In Proceedings of Blizzard Challenge Workshop (pp. 79\u201384). https:\/\/doi.org\/10.21437\/Blizzard.2017-13","journal-title":"Proceedings of Blizzard Challenge Workshop"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci12040443"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e31826fe79e"},{"key":"e_1_3_2_18_1","unstructured":"Jiang Z. Liu J. Ren Y. He J. Ji S. Zhang C. Ye Z. Wei P. Wang C. Yin X. Ma Z. & Zhao Z. (2023). Mega-TTS 2: Boosting prompting mechanisms for zero-shot speech synthesis. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2307.07218"},{"key":"e_1_3_2_19_1","unstructured":"Ju Z. Wang Y. Shen K. Tan X. Xin D. Yang D. Liu Y. Leng Y. Song K. Tang S. Wu Z. Qin T. Li X. Ye W. Zhang S. Bian J. He L. Li J. & Zhao S. (2024). NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2403.03100"},{"key":"e_1_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Kharitonov E. Vincent D. Borsos Z. Marinier R. Girgin S. Pietquin O. Sharifi M. Tagliasacchi M. & Zeghidour N. (2023). Speak read and prompt: High-fidelity text-to-speech with minimal supervision. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2302.03540","DOI":"10.1162\/tacl_a_00618"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v082.i13"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1080\/14992027.2017.1324643"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.3582148"},{"key":"e_1_3_2_24_1","volume-title":"Speech and the hearing-impaired child: Theory and practice","author":"Ling D.","year":"2002","unstructured":"Ling, D. (2002). Speech and the hearing-impaired child: Theory and practice (2nd ed.). Alexander Graham Bell Association for the Deaf and Hard of Hearing.","edition":"2"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e31826d0bc6"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1097\/MAO.0b013e318286836b"},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2019.01.011"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10162-008-0143-x"},{"key":"e_1_3_2_29_1","first-page":"1456","article-title":"Perception of synthetic speech in adult users of cochlear implants","author":"Nagao K.","year":"2012","unstructured":"Nagao, K., Paullin, M., Polikoff, J. B., Lilley, J., & Bunnell, H. T. (2012). Perception of synthetic speech in adult users of cochlear implants. In Proceedings of Interspeech (pp. 1456\u20131459). https:\/\/doi.org\/10.21437\/Interspeech.2012-413","journal-title":"In Proceedings of Interspeech"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.5122192"},{"key":"e_1_3_2_31_1","volume-title":"Modeling of transport demand: Analyzing, calculating, and forecasting transport demand","author":"Profillidis V.","year":"2018","unstructured":"Profillidis, V., & Botzoris, G. (2018). Modeling of transport demand: Analyzing, calculating, and forecasting transport demand. Elsevier. https:\/\/doi.org\/10.1016\/B978-0-12-811513-8.00003-0"},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2018.07.039"},{"key":"e_1_3_2_33_1","first-page":"10674","author":"Rombach R.","year":"2022","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 10674\u201310685). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01042","journal-title":"Proceedings of 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_34_1","first-page":"225","article-title":"IEEE recommended practice for speech quality measurements","volume":"17","author":"Rothauser E. H.","year":"2016","unstructured":"Rothauser, E. H., Chapman, W. D., Guttman, N., Silbiger, H. R., & Weinstock, M. (2016). IEEE recommended practice for speech quality measurements. IEEE Transactions on Audio and Electroacoustics, 17, 225\u2013246. https:\/\/doi.org\/10.1109\/IEEESTD.1969.7405210","journal-title":"IEEE Transactions on Audio and Electroacoustics"},{"key":"e_1_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.4863654"},{"key":"e_1_3_2_36_1","unstructured":"Shen K. Ju Z. Tan X. Liu Y. Leng Y. He L. Qin T. Zhao S. & Bian J. (2023). NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2304.09116"},{"key":"e_1_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.5037590"},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.007"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1177\/2331216516654022"},{"key":"e_1_3_2_40_1","volume-title":"R: A language and environment for statistical computing","author":"R Core Team","year":"2021","unstructured":"R Core Team. (2021). R: A language and environment for statistical computing. R Foundation for Statistical Computing."},{"key":"e_1_3_2_41_1","unstructured":"Vaswani A. Shazeer N. Parmar N. Uszkoreit J. Jones L. Gomez A.N. Kaiser L. & Polosukhin I. (2017). Attention is all you need. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1706.03762"},{"key":"e_1_3_2_42_1","unstructured":"Wang C. Chen S. Wu Y. Zhang Z. Zhou L. Liu S. Chen Z. Liu Y. Wang H. Li J. He L. Zhao S. & Wei F. (2023). Neural codec language models are zero-shot text to speech synthesizers. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2301.02111"},{"key":"e_1_3_2_43_1","doi-asserted-by":"crossref","unstructured":"Wei J. Wang X. Schuurmans D. Bosma M. Chi E.H. Xia F. Le Q. & Zhou D. (2022). Chain-of-thought prompting elicits reasoning in large language models. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2201.11903","DOI":"10.52202\/068431-1800"},{"key":"e_1_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e31803154d0"},{"key":"e_1_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.3109\/14992027.2011.642011"},{"key":"e_1_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1177\/23312165221134007"},{"key":"e_1_3_2_47_1","doi-asserted-by":"crossref","unstructured":"Xie T. Rong Y. Zhang P. & Liu L. (2024). Towards controllable speech synthesis in the era of large language models: A survey. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2412.06602","DOI":"10.18653\/v1\/2025.emnlp-main.40"},{"key":"e_1_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2023.111444"},{"key":"e_1_3_2_49_1","first-page":"593","author":"Yu Z.","year":"2010","unstructured":"Yu, Z., Yue, D., Zu, Y., & Chen, G. (2010). Word intelligibility testing and TTS system improvement. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010) (pp. 593\u2013596). https:\/\/doi.org\/10.1109\/ICOSP.2010.5655862","journal-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)"},{"key":"e_1_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"e_1_3_2_51_1","unstructured":"Zhang C. Zhang C. Zheng S. Zhang M. Qamar M. Bae S. & Kweon I. (2023). A survey on audio diffusion models: Text to speech synthesis and enhancement in generative AI. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2303.13336"},{"key":"e_1_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e3181b4aba8"},{"key":"e_1_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/14992020902902658"},{"key":"e_1_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1097\/MAO.0b013e318287ca86"},{"key":"e_1_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.3109\/00016489.2011.653668"}],"container-title":["Journal of Speech, Language, and Hearing Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.asha.org\/doi\/pdf\/10.1044\/2026_JSLHR-25-00295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T13:40:18Z","timestamp":1786455618000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.asha.org\/doi\/10.1044\/2026_JSLHR-25-00295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":54,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,11]]}},"alternative-id":["10.1044\/2026_JSLHR-25-00295"],"URL":"https:\/\/doi.org\/10.1044\/2026_jslhr-25-00295","relation":{},"ISSN":["1092-4388","1558-9102"],"issn-type":[{"value":"1092-4388","type":"print"},{"value":"1558-9102","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]}}}