{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T12:47:15Z","timestamp":1792154835620,"version":"4.4.0"},"reference-count":55,"publisher":"Acoustical Society of America (ASA)","issue":"4","funder":[{"DOI":"10.13039\/100000055","name":"National Institute on Deafness and Other Communication Disorders","doi-asserted-by":"publisher","award":["R21DC022428"],"award-info":[{"award-number":["R21DC022428"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:p>The current study involved the ability of deep-learning based noise reduction to generalize to accented-English speech. The deep neural network (DNN) was trained using a large number of different speakers (and different noises) of primarily standard native American English. This model was used to remove background noise from speech produced by 88 speakers having 9 different native-language backgrounds, who spoke English as a second language. The resulting speech was characterized by accents strong enough to substantially affect intelligibility. Objective measures of intelligibility, which reflect acoustic accuracy of the signal following noise reduction, indicated that the DNN generalized to accented speech well. Human-subjects intelligibility testing supported this conclusion. These results are promising in terms of the ability to deploy DNN-based noise reduction in hearing devices to broad populations, including those who receive speech from non-native speakers. Additional objective measures of speech quality indicated that the DNN led to slightly higher subjective sound quality for speech that had lesser accents and was more similar to the speech used for model training. This result suggests that expanding the training set to include accented speech has the potential to improve subjective sound quality of the processed signal.<\/jats:p>","DOI":"10.1121\/10.0046815","type":"journal-article","created":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T11:53:29Z","timestamp":1792151609000},"page":"3107-3118","update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Generalization of deep neural-network based noise reduction to accented-English speech"],"prefix":"10.1121","volume":"160","author":[{"given":"Eric W.","family":"Healy","sequence":"first","affiliation":[{"name":"Department of Speech and Hearing Science and Center for Cognitive and Brain Sciences, The Ohio State University , Columbus, Ohio 43210,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8010-602X","authenticated-orcid":false,"given":"Kian","family":"Fallah","sequence":"additional","affiliation":[{"name":"Department of Speech and Hearing Science and Center for Cognitive and Brain Sciences, The Ohio State University , Columbus, Ohio 43210,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah E.","family":"Yoho","sequence":"additional","affiliation":[{"name":"Department of Speech and Hearing Science and Center for Cognitive and Brain Sciences, The Ohio State University , Columbus, Ohio 43210,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"231","published-online":{"date-parts":[[2026,10,16]]},"reference":[{"key":"2026101607532254800_c1","volume-title":"American National Standard Methods for Manual Pure-Tone Threshold Audiometry","author":"ANSI","year":"2023"},{"key":"2026101607532254800_c2","volume-title":"American National Standard Specification for Audiometers","author":"ANSI","year":"2025"},{"key":"2026101607532254800_c3","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.heares.2009.06.005","article-title":"On the number of auditory filter outputs needed to understand speech: Further evidence for auditory channel independence","volume":"255","year":"2009","journal-title":"Hear. Res."},{"key":"2026101607532254800_c4","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1097\/AUD.0000000000000896","article-title":"The challenge of listening at home: Speech and noise levels in homes of young children with hearing loss","volume":"41","year":"2020","journal-title":"Ear Hear."},{"issue":"1","key":"2026101607532254800_c5","doi-asserted-by":"publisher","first-page":"13241","DOI":"10.1038\/s41598-024-63675-8","article-title":"Deep learning restores speech intelligibility in multi-talker interference for cochlear implant users","volume":"14","year":"2024","journal-title":"Sci. Rep."},{"key":"2026101607532254800_c6","unstructured":"Bradlow, A. R. (2026). \u201cALLSSTAR: Archive of L1 and L2 scripted and spontaneous transcripts and recordings,\u201d https:\/\/speechbox.linguistics.northwestern.edu\/allsstar (Last viewed 3\/30\/2026)."},{"issue":"7","key":"2026101607532254800_c7","first-page":"28","article-title":"Deep neural networks in hearing devices","volume":"28","year":"2021","journal-title":"Hear. Rev."},{"key":"2026101607532254800_c8","doi-asserted-by":"publisher","first-page":"2604","DOI":"10.1121\/1.4948445","article-title":"Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises","volume":"139","year":"2016","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c9","volume-title":"Hearing Aids","year":"2012"},{"key":"2026101607532254800_c10","doi-asserted-by":"publisher","first-page":"1677482","DOI":"10.3389\/fauot.2025.1677482","article-title":"Effectiveness of deep neural networks in hearing aids for improving signal-to-noise ratio, speech recognition, and listener preference in background noise","volume":"3","year":"2025","journal-title":"Front. Audiol. Otol."},{"key":"2026101607532254800_c11","doi-asserted-by":"publisher","first-page":"3497","DOI":"10.21437\/Interspeech.2023-975","article-title":"Joint compensation of multi-talker noise and reverberation for speech enhancement with cochlear implants using one or more microphones","volume":"2023","year":"2023","journal-title":"Proc. Interspeech"},{"key":"2026101607532254800_c12","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.heares.2016.11.012","article-title":"Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users","volume":"344","year":"2017","journal-title":"Hear. Res."},{"key":"2026101607532254800_c13","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1121\/1.5119226","article-title":"Using recurrent neural networks to improve the perception of speech in non-stationary noise by people with cochlear implants","volume":"146","year":"2019","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c14","first-page":"75","article-title":"Foreign accent","volume-title":"Speaker Classification I: Fundamentals, Features, and Methods","author":"M\u00fcller","year":"2007"},{"key":"2026101607532254800_c15","unstructured":"Hasemann, H., and Krylova, A. (2024). \u201cRevolutionary speech understanding with spheric speech clarity,\u201d https:\/\/auditorycenter.com\/wp-content\/uploads\/2024\/08\/Phonak-Insight-Spheric-Speech-Clarity.pdf."},{"key":"2026101607532254800_c16","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1121\/10.0006565","article-title":"Deep learning based speaker separation and dereverberation can generalize across different languages to improve intelligibility","volume":"150","year":"2021","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c17","doi-asserted-by":"publisher","first-page":"4106","DOI":"10.1121\/10.0001441","article-title":"A talker-independent deep learning algorithm to increase intelligibility for hearing-impaired listeners in reverberant competing talker conditions","volume":"147","year":"2020","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c18","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.1121\/10.0019341","article-title":"Progress made in the efficacy and viability of deep-learning-based noise reduction","volume":"153","year":"2023","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c19","doi-asserted-by":"publisher","first-page":"3976","DOI":"10.1121\/10.0007134","article-title":"A causal and talker-independent speaker-separation\/dereverberation deep learning algorithm: Cost associated with conversion to real-time capable operation","volume":"150","year":"2021","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c20","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1121\/1.4929493","article-title":"An algorithm to increase speech intelligibility for hearing-impaired listeners in novel segments of the same noise type","volume":"138","year":"2015","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c21","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1121\/10.0037197","article-title":"Perceptual effects of reducing algorithmic latency on deep-learning based noise reduction","volume":"158","year":"2025","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c22","doi-asserted-by":"publisher","first-page":"3029","DOI":"10.1121\/1.4820893","article-title":"An algorithm to improve speech recognition in noise for hearing-impaired listeners","volume":"134","year":"2013","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c23","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","year":"1997","journal-title":"Neural Comput."},{"key":"2026101607532254800_c24","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1121\/1.5094765","article-title":"Comparison of effects on subjective intelligibility and quality of speech in babble for two algorithms: A deep recurrent neural network and spectral subtraction","volume":"145","year":"2019","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c25","unstructured":"Kingma, D. P., and Ba, J. (2014). \u201cAdam: A method for stochastic optimization,\u201d arXiv:1412.6980."},{"key":"2026101607532254800_c26","first-page":"626","article-title":"SDR\u2014half-baked or well done?","year":"2019"},{"key":"2026101607532254800_c27","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1121\/10.0003626","article-title":"A method for realistic, conversational signal-to-noise ratio estimation","volume":"149","year":"2021","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c28","volume-title":"Cochlear Hearing Loss: Physiological, Psychological and Technical Issues","year":"2007","edition":"2"},{"key":"2026101607532254800_c29","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s10162-026-01031-5","article-title":"Hearing aids: What works well and what can be improved","volume":"27","year":"2026","journal-title":"J. Assoc. Res. Otolaryngol."},{"key":"2026101607532254800_c30","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1121\/1.408469","article-title":"Development of the hearing in noise test for the measurement of speech reception thresholds in quiet and in noise","volume":"95","year":"1994","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c31","first-page":"5206","article-title":"LibriSpeech: An ASR corpus based on public domain audio books","year":"2015"},{"key":"2026101607532254800_c32","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.1109\/TASLP.2022.3161143","article-title":"Self-attending RNN for speech enhancement to improve cross-corpus generalization","volume":"30","year":"2022","journal-title":"IEEE\/ACM Trans. Audio. Speech Lang. Process."},{"key":"2026101607532254800_c33","first-page":"357","article-title":"The design for the Wall Street Journal-based CSR corpus","year":"1992"},{"key":"2026101607532254800_c34","unstructured":"Pearsons, K. S., Bennett, R. L., and Fidell, S. A. (1977). Speech Levels in Various Noise Environments (Office of Health and Ecological Effects, Office of Research and Development, U.S. Environmental Protection Agency, Washington, DC)."},{"key":"2026101607532254800_c35","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1121\/1.381753","article-title":"Auditory handicap of hearing impairment and the limited benefit of hearing aids","volume":"63","year":"1978","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c36","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)\u2014a new method for speech quality assessment of telephone networks and codecs","year":"2001"},{"key":"2026101607532254800_c37","unstructured":"Santurette, S., and Behrens, T. (2020). \u201cThe audiology of Oticon More\u2122,\u201d Oticon white paper, https:\/\/assets-we.cas.dgs.com\/-\/media\/oticon\/main\/pdf\/master\/whitepaper\/69619uk_wp_oticon_more_audiology.pdf (Last viewed 8\/29\/2026)."},{"key":"2026101607532254800_c38","doi-asserted-by":"publisher","first-page":"1746635","DOI":"10.3389\/fauot.2025.1746635","article-title":"Effects of low-latency deep-learning-based noise reduction on speech intelligibility for normal hearing, hearing-impaired listeners and cochlear implant users","volume":"3","year":"2026","journal-title":"Front. Audiol. Otol."},{"key":"2026101607532254800_c39","doi-asserted-by":"publisher","first-page":"183","DOI":"10.3766\/jaaa.26.2.7","article-title":"Estimation of signal-to-noise ratios in realistic sound scenarios","volume":"26","year":"2015","journal-title":"J. Am. Acad. Audiol."},{"key":"2026101607532254800_c40","unstructured":"Sound Ideas (2026). https:\/\/sound-ideas.com\/ (Last viewed 3\/31\/2026)."},{"key":"2026101607532254800_c41","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.1044\/2019_JSLHR-S-17-0414","article-title":"Accent intelligibility differences in noise across native and nonnative accents: Effects of talker\u2013listener pairing at acoustic\u2013phonetic and lexical levels","volume":"62","year":"2019","journal-title":"J. Speech Lang. Hear. Res."},{"key":"2026101607532254800_c55","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1044\/jshr.2803.455","article-title":"A \u2018rationalized\u2019 arcsine transform","volume":"28","year":"1985","journal-title":"J. Speech, Lang., Hear. Res."},{"key":"2026101607532254800_c42","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","article-title":"An algorithm for intelligibility prediction of time\u2013frequency weighted noisy speech","volume":"19","year":"2011","journal-title":"IEEE Trans. Audio. Speech Lang. Process."},{"key":"2026101607532254800_c43","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1121\/10.0028007","article-title":"Using deep learning to improve the intelligibility of a target speaker in noisy multi-talker environments for people with normal hearing and hearing loss","volume":"156","year":"2024","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c44","unstructured":"U.S. Census Bureau (2026). https:\/\/data.census.gov\/ (Last viewed 8\/29\/2026)."},{"key":"2026101607532254800_c45","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems","volume":"12","year":"1993","journal-title":"Speech Commun."},{"key":"2026101607532254800_c46","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). \u201cAttention is all you need,\u201d arXiv:1706.03762."},{"key":"2026101607532254800_c47","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1109\/TASL.2013.2250961","article-title":"Towards scaling up classification-based speech separation","volume":"21","year":"2013","journal-title":"IEEE Trans. Audio. Speech Lang. Process."},{"key":"2026101607532254800_c48","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","article-title":"Complex ratio masking for monaural speech separation","volume":"24","year":"2016","journal-title":"IEEE\/ACM Trans. Audio. Speech Lang. Process."},{"key":"2026101607532254800_c49","unstructured":"Wright, A., Keller, M., Kuehnel, V., Latzel, M., and Seitz-Paquette, K. (2024). \u201cSpheric speech clarity applies DNN processing to significantly improve speech understanding from any direction and reduce the listening effort,\u201d https:\/\/www.phonak.com\/evidence."},{"key":"2026101607532254800_c50","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1097\/AUD.0000000000000486","article-title":"Characteristics of real-world signal to noise ratios and speech listening situations of older adults with mild to moderate hearing loss","volume":"39","year":"2018","journal-title":"Ear Hear."},{"key":"2026101607532254800_c51","doi-asserted-by":"publisher","first-page":"3322","DOI":"10.1121\/10.0001141","article-title":"Comparing non-native and native speech: Are L2 productions more variable?","volume":"147","year":"2020","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c52","doi-asserted-by":"publisher","first-page":"558","DOI":"10.3758\/s13414-018-1635-3","article-title":"Are there sex effects for speech intelligibility in American English? Examining the influence of talker, listener, and methodology","volume":"81","year":"2019","journal-title":"Atten. Percept. Psychophys."},{"key":"2026101607532254800_c53","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1121\/1.5055562","article-title":"A deep learning based segregation algorithm to increase speech intelligibility for hearing-impaired listeners in reverberant-noisy conditions","volume":"144","year":"2018","journal-title":"J. Acoust. Soc. Am."},{"key":"2026101607532254800_c54","doi-asserted-by":"publisher","first-page":"103069","DOI":"10.1016\/j.lingua.2021.103069","article-title":"Acoustic salience in the evaluations of intelligibility and foreign accentedness of nonnative vowel production","volume":"256","year":"2021","journal-title":"Lingua"}],"container-title":["The Journal of the Acoustical Society of America"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/160\/4\/3107\/21172793\/3107_1_10.0046815.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/160\/4\/3107\/21172793\/3107_1_10.0046815.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T11:53:35Z","timestamp":1792151615000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jasa\/article\/160\/4\/3107\/3406680\/Generalization-of-deep-neural-network-based-noise"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1121\/10.0046815","relation":{},"ISSN":["1520-8524"],"issn-type":[{"value":"1520-8524","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,10,1]]}}}