{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T08:01:59Z","timestamp":1777881719807,"version":"3.51.4"},"reference-count":54,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001230","name":"Macquarie University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001230","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Trends in Hearing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>\n                    Individuals regularly experience\n                    <jats:italic toggle=\"yes\">Hearing Difficulty Moments<\/jats:italic>\n                    in everyday conversation. Identifying Hearing Difficulty Moments has particular significance in the field of hearing assistive technology where timely interventions are key for real-time hearing assistance. In this article, we propose and compare machine learning solutions for the temporal detection of segments containing Hearing Difficulty Moments in conversational audio. We show that audio language models, through their multimodal reasoning capabilities, can achieve state-of-the-art results for this task, significantly outperforming a simple automatic speech recognition (ASR) hotword heuristic and a more conventional fine-tuning approach with Wav2Vec, an audio-only input architecture that is state-of-the-art for ASR.\n                  <\/jats:p>","DOI":"10.1177\/23312165261446379","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T13:38:38Z","timestamp":1776951518000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Identifying Hearing Difficulty Moments in Conversational Audio"],"prefix":"10.1177","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4474-4810","authenticated-orcid":false,"given":"Jack","family":"Collins","sequence":"first","affiliation":[{"name":"Google Research Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Buzea","sequence":"additional","affiliation":[{"name":"Google Research Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chris","family":"Collier","sequence":"additional","affiliation":[{"name":"Google Research Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro Ballesta","family":"Rosen","sequence":"additional","affiliation":[{"name":"Google Research Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7073-2926","authenticated-orcid":false,"given":"Julian","family":"Maclaren","sequence":"additional","affiliation":[{"name":"Google Research Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2348-811X","authenticated-orcid":false,"given":"Richard F.","family":"Lyon","sequence":"additional","affiliation":[{"name":"Google Research Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kelly","family":"Miles","sequence":"additional","affiliation":[{"name":"Macquarie University Hearing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1079-3067","authenticated-orcid":false,"given":"Simon","family":"Carlile","sequence":"additional","affiliation":[{"name":"Google Research Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"crossref","unstructured":"Alghamdi E. Halvey M. Nicol E. (2024). System and user strategies to repair conversational breakdowns of spoken dialogue systems: A scoping review. In Proceedings of the 6th ACM conference on conversational user interfaces (pp. 1\u201313).","DOI":"10.1145\/3640794.3665558"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000001061"},{"key":"e_1_3_3_4_1","unstructured":"Baevski A. Zhou Y. Mohamed A. Auli M. (2020). wav2vec 2.0: A framework for self-supervised learning of speech representations. In H. Larochelle M. Ranzato R. Hadsell M. Balcan & H. Lin (Eds.) Advances in neural information processing systems (Vol. 33 pp. 12449\u201312460). Curran Associates Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/92d1e1eb1cd6f9fba3227870bb6d7f07-Paper.pdf."},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1044\/2020_JSLHR-19-00350"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1163\/000579511X605759"},{"issue":"6","key":"e_1_3_3_7_1","first-page":"22","article-title":"Disparity between clinical assessment and real-world performance of hearing aids","volume":"14","author":"Cord M.","year":"2007","unstructured":"Cord M., Baskent D., Kalluri S., Moore B. (2007). Disparity between clinical assessment and real-world performance of hearing aids. Hearing Review, 14(6), 22.","journal-title":"Hearing Review"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.3766\/jaaa.15.5.3"},{"key":"e_1_3_3_9_1","unstructured":"Core M. Allen J. (2001). Coding dialogs with the damsl annotation scheme https:\/\/www.eecis.udel.edu\/carberry\/CIS-885\/Papers\/Core-Allen-Coding-Damsl.pdf."},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1353\/lan.2006.0130"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0136100"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00080-8"},{"key":"e_1_3_3_13_1","unstructured":"Gemini Team Google (2024) Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. Technical report Google. https:\/\/storage.googleapis.com\/deepmind-media\/gemini\/gemini_v1_5_report.pdf."},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-46416-0"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0258247"},{"key":"e_1_3_3_16_1","unstructured":"Hassabis D. Pichai S. (2024). Our next-generation models are here: Gemini 2.0 and Gemini 2.0 flash. The Keyword (Google Blog). https:\/\/blog.google\/technology\/google-deepmind\/google-gemini-ai-update-december-2024."},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.241632"},{"key":"e_1_3_3_18_1","unstructured":"Hu E. J. Shen Y. Wallis P. Allen-Zhu Z. Li Y. Wang S. Wang L. Chen W. (2021). Lora: Low-rank adaptation of large language models. https:\/\/arxiv.org\/abs\/2106.09685."},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.405631"},{"key":"e_1_3_3_20_1","unstructured":"Jurafsky D. Shriberg E. Biasca D. (1997). Switchboard swbd-damsl shallow-discourse-function annotation coders manual draft 13. Tech. Rep. 97-02. Boulder CO USA. https:\/\/web.stanford.edu\/jurafsky\/ws97\/manual.august1.html."},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.00250"},{"key":"e_1_3_3_22_1","unstructured":"Khanpour H. Guntakandla N. Nielsen R. (2016). Dialogue act classification in domain-independent conversations using a deep recurrent neural network. In Y. Matsumoto & R. Prasad (Eds.) Proceedings of COLING 2016 the 26th International conference on computational linguistics: technical papers (pp. 2012\u20132021). Osaka Japan: The COLING 2016 Organizing Committee. https:\/\/aclanthology.org\/C16-1189\/."},{"key":"e_1_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Ko T. Peddinti V. Povey D. Khudanpur S. (2015). Audio augmentation for speech recognition. In Proceeding of the Interspeech (pp. 3586\u20133589). https:\/\/doi.org\/10.21437\/Interspeech.2015-711","DOI":"10.21437\/Interspeech.2015-711"},{"key":"e_1_3_3_24_1","doi-asserted-by":"crossref","unstructured":"Lee J. Y. Dernoncourt F. (2016). Sequential short-text classification with recurrent and convolutional neural networks. In K. Knight A. Nenkova & O. Rambow (Eds.) Proceedings of the 2016 Conference of the North American chapter of the association for computational linguistics: Human language technologies (pp. 515\u2013520). San Diego California: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N16-1062","DOI":"10.18653\/v1\/N16-1062"},{"key":"e_1_3_3_25_1","first-page":"1","article-title":"Timing in turn-taking in conversation","volume":"6","author":"Levinson S. C.","year":"2015","unstructured":"Levinson S. C., Torreira F. (2015). Timing in turn-taking in conversation. Frontiers in Psychology, 6, 1\u201314. https:\/\/doi.org\/10.3389\/fpsyg.2015.00634","journal-title":"Frontiers in Psychology"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1515\/opli-2016-0001"},{"key":"e_1_3_3_27_1","doi-asserted-by":"crossref","unstructured":"Miah M. M. M. Pyarelal A. Huang R. (2023). Hierarchical fusion for online multimodal dialog act classification. In H. Bouamor J. Pino & K. Bali (Eds.) Findings of the association for computational linguistics: EMNLP 2023 (pp. 7532\u20137545). Singapore: Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.505","DOI":"10.18653\/v1\/2023.findings-emnlp.505"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.789565"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-47396-y"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1121\/10.0000780"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1024068626366"},{"key":"e_1_3_3_32_1","doi-asserted-by":"crossref","unstructured":"Ortega D. Vu N. T. (2018). Lexico-acoustic neural-based models for dialog act classification. https:\/\/arxiv.org\/abs\/1803.00831.","DOI":"10.1109\/ICASSP.2018.8461371"},{"key":"e_1_3_3_33_1","doi-asserted-by":"crossref","unstructured":"Panayotov V. Chen G. Povey D. Khudanpur S. (2015). 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). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2024.1289637"},{"key":"e_1_3_3_35_1","doi-asserted-by":"crossref","unstructured":"Petersen E. Walravens E. Pedersen A. (2023). Backchannel behavior in conversations and how it is affected by hearing loss noise and hearing aids. https:\/\/doi.org\/10.61782\/fa.2023.0432","DOI":"10.61782\/fa.2023.0432"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0325244"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1044\/2024_JSLHR-23-00667"},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1044\/2018_JSLHR-H-17-0124"},{"key":"e_1_3_3_39_1","doi-asserted-by":"crossref","unstructured":"Salamon J. Jacoby C. Bello J. P. (2014). A dataset and taxonomy for urban sound research. In Proceedings of the 22nd ACM international conference on multimedia (pp. 1041\u20131044). New York NY USA: Association for Computing Machinery. https:\/\/doi.org\/10.1145\/2647868.2655045","DOI":"10.1145\/2647868.2655045"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/14992020701689696"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.2307\/413107"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000000421"},{"key":"e_1_3_3_43_1","doi-asserted-by":"crossref","unstructured":"Shriberg E. Dhillon R. Bhagat S. Ang J. Carvey H. (2004). The ICSI meeting recorder dialog act (MRDA) corpus. In Proceedings of the 5th SIGdial workshop on discourse and dialogue at HLT-NAACL 2004 (pp. 97\u2013100). Cambridge Massachusetts USA: Association for Computational Linguistics. https:\/\/aclanthology.org\/W04-2319\/","DOI":"10.21236\/ADA460980"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1177\/002383099804100410"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2025.1584937"},{"key":"e_1_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1177\/23312165241296073"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0903616106"},{"key":"e_1_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120100561737"},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.3766\/jaaa.15.5.2"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.5087567"},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1121\/10.0004774"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.395965"},{"key":"e_1_3_3_53_1","first-page":"1","article-title":"Efficacy and effectiveness of advanced hearing aid directional and noise reduction technologies for older adults with mild to moderate hearing loss","volume":"40","author":"Wu Y. H.","year":"2018","unstructured":"Wu Y. H., Stangl E., Chipara O., Hasan S., DeVries S., Oleson J. (2018). Efficacy and effectiveness of advanced hearing aid directional and noise reduction technologies for older adults with mild to moderate hearing loss. Ear and Hearing, 40, 1. https:\/\/doi.org\/10.1097\/AUD.0000000000000672","journal-title":"Ear and Hearing"},{"key":"e_1_3_3_54_1","doi-asserted-by":"crossref","unstructured":"Yin Y. Ananthabhotla I. Ithapu V. K. Petridis S. Wu Y. H. Miller C. (2024). Hearing loss detection from facial expressions in one-on-one conversations. In IEEE International conference on acoustics speech and signal processing (ICASSP) (pp. 5460\u20135464). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10446324","DOI":"10.1109\/ICASSP48485.2024.10446324"},{"key":"e_1_3_3_55_1","unstructured":"Zhang Y. Han W. Qin J. Wang Y. Bapna A. Chen Z. Chen N. Li B. Axelrod V. Wang G. Meng Z. Hu K. Rosenberg A. Prabhavalkar R. Park D. S. Haghani P. Riesa J. Perng G. Soltau H. Wu Y. (2023). Google USM: Scaling automatic speech recognition beyond 100 languages. https:\/\/arxiv.org\/abs\/2303.01037."}],"container-title":["Trends in Hearing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/23312165261446379","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/23312165261446379","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/23312165261446379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:51:06Z","timestamp":1777596666000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/23312165261446379"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":54,"alternative-id":["10.1177\/23312165261446379"],"URL":"https:\/\/doi.org\/10.1177\/23312165261446379","relation":{},"ISSN":["2331-2165","2331-2165"],"issn-type":[{"value":"2331-2165","type":"print"},{"value":"2331-2165","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"article-number":"23312165261446379"}}