{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:23:00Z","timestamp":1780604580652,"version":"3.54.1"},"reference-count":57,"publisher":"Acoustical Society of America (ASA)","issue":"3","license":[{"start":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T00:00:00Z","timestamp":1490140800000},"content-version":"vor","delay-in-days":21,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T00:00:00Z","timestamp":1490140800000},"content-version":"tdm","delay-in-days":21,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,3,1]]},"abstract":"<jats:p>Machine-learning based approaches to speech enhancement have recently shown great promise for improving speech intelligibility for hearing-impaired listeners. Here, the performance of three machine-learning algorithms and one classical algorithm, Wiener filtering, was compared. Two algorithms based on neural networks were examined, one using a previously reported feature set and one using a feature set derived from an auditory model. The third machine-learning approach was a dictionary-based sparse-coding algorithm. Speech intelligibility and quality scores were obtained for participants with mild-to-moderate hearing impairments listening to sentences in speech-shaped noise and multi-talker babble following processing with the algorithms. Intelligibility and quality scores were significantly improved by each of the three machine-learning approaches, but not by the classical approach. The largest improvements for both speech intelligibility and quality were found by implementing a neural network using the feature set based on auditory modeling. Furthermore, neural network based techniques appeared more promising than dictionary-based, sparse coding in terms of performance and ease of implementation.<\/jats:p>","DOI":"10.1121\/1.4977197","type":"journal-article","created":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T16:07:24Z","timestamp":1490198844000},"page":"1985-1998","update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":25,"title":["Auditory inspired machine learning techniques can improve speech intelligibility and quality for hearing-impaired listeners"],"prefix":"10.1121","volume":"141","author":[{"given":"Jessica J. M.","family":"Monaghan","sequence":"first","affiliation":[{"name":"University of Southampton Institute of Sound and Vibration Research, , Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Goehring","sequence":"additional","affiliation":[{"name":"University of Southampton Institute of Sound and Vibration Research, , Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Southampton Institute of Sound and Vibration Research, , Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Bolner","sequence":"additional","affiliation":[{"name":"Katholieke Universiteit Leuven ExpORL, , Leuven, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangqiguo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Southampton Institute of Sound and Vibration Research, , Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew C. M.","family":"Wright","sequence":"additional","affiliation":[{"name":"University of Southampton Institute of Sound and Vibration Research, , Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Bleeck","sequence":"additional","affiliation":[{"name":"University of Southampton Institute of Sound and Vibration Research, , Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"231","published-online":{"date-parts":[[2017,3,22]]},"reference":[{"key":"2023080804363105000_c1","doi-asserted-by":"publisher","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","article-title":"K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation","volume":"54","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"2023080804363105000_c2","volume-title":"American National Standard Methods for Calculation of the Speech Intelligibility Index","author":"ANSI","year":"1997"},{"key":"2023080804363105000_c3","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1016\/S0167-6393(02)00183-8","article-title":"Evaluation of an auditory masked threshold noise suppression algorithm in normal-hearing and hearing-impaired listeners","volume":"40","year":"2003","journal-title":"Speech Commun."},{"key":"2023080804363105000_c4","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1080\/14992020802033091","article-title":"Digital noise reduction: Outcomes from laboratory and field studies","volume":"47","year":"2008","journal-title":"Int. J. Audiol."},{"key":"2023080804363105000_c5","first-page":"781","article-title":"Aim-mat: The auditory image model in MATLAB","volume":"90","year":"2004","journal-title":"Acta Acust. Acust."},{"key":"2023080804363105000_c6","first-page":"6520","article-title":"Speech enhancement based on neural networks applied to cochlear implant coding strategies","year":"2016"},{"key":"2023080804363105000_c7","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1097\/00003446-198608000-00007","article-title":"The National Acoustic Laboratories' (NAL) new procedure for selecting the gain and frequency response of a hearing aid","volume":"7","year":"1986","journal-title":"Ear Hear."},{"key":"2023080804363105000_c56","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":"2023080804363105000_c8","doi-asserted-by":"crossref","first-page":"7940","DOI":"10.1523\/JNEUROSCI.23-21-07940.2003","article-title":"Binary spiking in auditory cortex","volume":"23","year":"2003","journal-title":"J. Neurosci."},{"key":"2023080804363105000_c9","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1214\/009053604000000067","article-title":"Least angle regression","volume":"32","year":"2004","journal-title":"Ann. Stat."},{"key":"2023080804363105000_c10","first-page":"895","article-title":"Image denoising via learned dictionaries and sparse representation","year":"2006"},{"key":"2023080804363105000_c11","doi-asserted-by":"publisher","first-page":"299","DOI":"10.3109\/14992027.2011.645075","article-title":"Measurement and prediction of the acceptable noise level for single-microphone noise reduction algorithms","volume":"51","year":"2012","journal-title":"Int. J. Audiol."},{"key":"2023080804363105000_c12","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM NIST speech disc 1-11","year":"1993"},{"key":"2023080804363105000_c13","first-page":"145","article-title":"Noise power estimation based on the probability of speech presence","year":"2011"},{"key":"2023080804363105000_c14","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":"2016","journal-title":"Hearing Res."},{"key":"2023080804363105000_c15","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":"2023080804363105000_c16","doi-asserted-by":"publisher","first-page":"3325","DOI":"10.1121\/1.4901712","article-title":"Speech-cue transmission by an algorithm to increase consonant recognition in noise for hearing-impaired listeners","volume":"136","year":"2014","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c17","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."},{"issue":"4","key":"2023080804363105000_c18","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/89.326616","article-title":"RASTA processing of speech","volume":"2","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"2023080804363105000_c19","first-page":"433","article-title":"Frequency analysis and synthesis using a Gammatone filterbank","volume":"88","year":"2002","journal-title":"Acta Acust. Acust."},{"key":"2023080804363105000_c20","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.1121\/1.417354","article-title":"Speech intelligibility prediction in hearing-impaired listeners based on a psychoacoustically motivated perception model","volume":"100","year":"1996","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c21","first-page":"561","article-title":"A comparative intelligibility study of speech enhancement algorithms","year":"2007"},{"key":"2023080804363105000_c22","doi-asserted-by":"publisher","first-page":"3689","DOI":"10.1121\/1.3365256","article-title":"Environment-specific noise suppression for improved speech intelligibility by cochlear implant users","volume":"127","year":"2010","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c23","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0167-6393(00)00085-6","article-title":"Segregating information about the size and shape of the vocal tract using a time-domain auditory model: The stabilised wavelet-Mellin transform","volume":"36","year":"2002","journal-title":"Speech Commun."},{"key":"2023080804363105000_c24","first-page":"4164","article-title":"A multi-band spectral subtraction method for enhancing speech corrupted by colored noise","year":"2002"},{"key":"2023080804363105000_c25","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1121\/1.3184603","article-title":"An algorithm that improves speech intelligibility in noise for normal-hearing listeners","volume":"126","year":"2009","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c26","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1097\/00025572-200002000-00004","article-title":"MarkeTrak V: \u2018Why my hearing aids are in the drawer\u2019: The consumers' perspective","volume":"53","year":"2000","journal-title":"Hear. J."},{"key":"2023080804363105000_c27","first-page":"7","article-title":"Signal processing for hearing impairment","volume":"38","year":"1992","journal-title":"Scand. Audiol. Suppl."},{"key":"2023080804363105000_c28","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1038\/nn831","article-title":"Efficient coding of natural sounds","volume":"5","year":"2002","journal-title":"Nat. Neurosci."},{"issue":"12","key":"2023080804363105000_c29","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/PROC.1979.11540","article-title":"Enhancement and bandwidth compression of noisy speech","volume":"67","year":"1979","journal-title":"Proc. IEEE"},{"issue":"1","key":"2023080804363105000_c30","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/TASL.2010.2045180","article-title":"Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions","volume":"19","year":"2011","journal-title":"IEEE Trans. Audio Speech Language Process."},{"issue":"1","key":"2023080804363105000_c31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2009\/437807","article-title":"Low delay noise reduction and dereverberation for hearing aids","volume":"2009","year":"2009","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"2023080804363105000_c32","doi-asserted-by":"publisher","first-page":"1491","DOI":"10.1121\/1.3299168","article-title":"Multicenter evaluation of signal enhancement algorithms for hearing aids","volume":"127","year":"2010","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c33","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/TASL.2012.2213248","article-title":"The potential for speech intelligibility improvement using the ideal binary mask and the ideal wiener filter in single channel noise reduction systems: Application to auditory prostheses","volume":"21","year":"2013","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2023080804363105000_c34","doi-asserted-by":"publisher","first-page":"EL398","DOI":"10.1121\/1.4901133","article-title":"Requirements for the evaluation of computational speech segregation systems","volume":"136","year":"2014","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c35","doi-asserted-by":"publisher","first-page":"3066","DOI":"10.1121\/1.2932824","article-title":"Low-dimensional, auditory feature vectors that improve vocal-tract-length normalization in automatic speech recognition","volume":"123","year":"2008","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c36","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1177\/1084713806289553","article-title":"The effects of digital noise reduction on the acceptance of background noise","volume":"10","year":"2006","journal-title":"Trends Amplif."},{"key":"2023080804363105000_c57","first-page":"1364","article-title":"Enhancing vocal tract length normalization with elastic registration for automatic speech recognition","volume-title":"INTERSPEECH","year":"2012"},{"key":"2023080804363105000_c37","doi-asserted-by":"publisher","first-page":"626","DOI":"10.3766\/jaaa.17.9.2","article-title":"Acceptable noise level as a predictor of hearing aid use","volume":"17","year":"2006","journal-title":"J. Am. Acad. Audiol."},{"key":"2023080804363105000_c38","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","year":"1996","journal-title":"Nature"},{"key":"2023080804363105000_c39","first-page":"40","article-title":"Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition","year":"1993"},{"key":"2023080804363105000_c40","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.1121\/1.414456","article-title":"Time-domain modeling of peripheral auditory processing: A modular architecture and a software platform","volume":"98","year":"1995","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c41","first-page":"1","article-title":"An efficient auditory filterbank based on the gammatone function","year":"1987"},{"key":"2023080804363105000_c42","first-page":"586","article-title":"A direct adaptive method for faster backpropagation learning: The RPROP algorithm","year":"1993"},{"key":"2023080804363105000_c43","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1109\/TAU.1969.1162058","article-title":"IEEE recommended practice for speech quality measurements","volume":"17","year":"1969","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"2023080804363105000_c44","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.heares.2014.01.006","article-title":"Evaluation of the sparse coding shrinkage noise reduction algorithm in normal hearing and hearing impaired listeners","volume":"310","year":"2014","journal-title":"Hear. Res."},{"key":"2023080804363105000_c45","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.heares.2015.07.019","article-title":"Speech quality evaluation of a sparse coding shrinkage noise reduction algorithm with normal hearing and hearing impaired listeners","volume":"327","year":"2015","journal-title":"Hear. Res."},{"key":"2023080804363105000_c46","first-page":"629","article-title":"Speech enhancement based on a priori signal to noise estimation","year":"1996"},{"key":"2023080804363105000_c47","doi-asserted-by":"publisher","first-page":"1698","DOI":"10.1109\/TASL.2012.2187194","article-title":"Speech enhancement using generative dictionary learning","volume":"20","year":"2012","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"1","key":"2023080804363105000_c48","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1121\/1.1828637","article-title":"The processing and perception of size information in speech sounds","volume":"117","year":"2005","journal-title":"J. Acoust. Soc. Am."},{"key":"2023080804363105000_c49","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1097\/00003446-199906000-00002","article-title":"Tolerable hearing aid delays I Estimation of limits imposed by the auditory path alone using simulated hearing losses","volume":"20","year":"1999","journal-title":"Ear Hear."},{"key":"2023080804363105000_c50","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."},{"issue":"3","key":"2023080804363105000_c51","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/TSA.2003.811542","article-title":"SNR estimation based on amplitude modulation analysis with applications to noise suppression","volume":"11","year":"2003","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"2023080804363105000_c52","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1109\/89.641296","article-title":"Speech enhancement based on audible noise suppression","volume":"5","year":"1997","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"2023080804363105000_c53","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1016\/j.cub.2007.05.061","article-title":"Neural representation of auditory size in the human voice and in sounds from other resonant sources","volume":"17","year":"2007","journal-title":"Curr. Biol."},{"key":"2023080804363105000_c54","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 Language Process."},{"key":"2023080804363105000_c55","doi-asserted-by":"publisher","first-page":"853","DOI":"10.3109\/14992020903131117","article-title":"Environmental noise reduction configuration: Effects on preferences, satisfaction, and speech understanding","volume":"48","year":"2009","journal-title":"Int. J. Audiol."}],"container-title":["The Journal of the Acoustical Society of America"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/141\/3\/1985\/15324455\/1985_1_online.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/141\/3\/1985\/15324455\/1985_1_online.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/asa\/jasa\/article-pdf\/141\/3\/1985\/15324455\/1985_1_online.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T19:14:25Z","timestamp":1748373265000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jasa\/article\/141\/3\/1985\/1056492\/Auditory-inspired-machine-learning-techniques-can"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,1]]},"references-count":57,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,3,1]]}},"URL":"https:\/\/doi.org\/10.1121\/1.4977197","relation":{},"ISSN":["0001-4966","1520-8524"],"issn-type":[{"value":"0001-4966","type":"print"},{"value":"1520-8524","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,3]]},"published":{"date-parts":[[2017,3,1]]}}}