Speech Enhancement for Hearing Impaired Based on Bandpass Filters and a Compound Deep Denoising Autoencoder
Deep neural networks have been applied for speech enhancements efficiently. However, for large variations of speech patterns and noisy environments, an individual neural network with a fixed number of hidden layers causes strong interference, which can lead to a slow learning process, poor generalis...
Saved in:
| Published in: | Symmetry (Basel) Vol. 13; no. 8; p. 1310 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Basel
MDPI AG
01.08.2021
|
| Subjects: | |
| ISSN: | 2073-8994, 2073-8994 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Deep neural networks have been applied for speech enhancements efficiently. However, for large variations of speech patterns and noisy environments, an individual neural network with a fixed number of hidden layers causes strong interference, which can lead to a slow learning process, poor generalisation in an unknown signal-to-noise ratio in new inputs, and some residual noise in the enhanced output. In this paper, we present a new approach for the hearing impaired based on combining two stages: (1) a set of bandpass filters that split up the signal into eight separate bands each performing a frequency analysis of the speech signal; (2) multiple deep denoising autoencoder networks, with each working for a small specific enhancement task and learning to handle a subset of the whole training set. To evaluate the performance of the approach, the hearing-aid speech perception index, the hearing aid sound quality index, and the perceptual evaluation of speech quality were used. Improvements in speech quality and intelligibility were evaluated using seven subjects of sensorineural hearing loss audiogram. We compared the performance of the proposed approach with individual denoising autoencoder networks with three and five hidden layers. The experimental results showed that the proposed approach yielded higher quality and was more intelligible compared with three and five layers. |
|---|---|
| AbstractList | Deep neural networks have been applied for speech enhancements efficiently. However, for large variations of speech patterns and noisy environments, an individual neural network with a fixed number of hidden layers causes strong interference, which can lead to a slow learning process, poor generalisation in an unknown signal-to-noise ratio in new inputs, and some residual noise in the enhanced output. In this paper, we present a new approach for the hearing impaired based on combining two stages: (1) a set of bandpass filters that split up the signal into eight separate bands each performing a frequency analysis of the speech signal; (2) multiple deep denoising autoencoder networks, with each working for a small specific enhancement task and learning to handle a subset of the whole training set. To evaluate the performance of the approach, the hearing-aid speech perception index, the hearing aid sound quality index, and the perceptual evaluation of speech quality were used. Improvements in speech quality and intelligibility were evaluated using seven subjects of sensorineural hearing loss audiogram. We compared the performance of the proposed approach with individual denoising autoencoder networks with three and five hidden layers. The experimental results showed that the proposed approach yielded higher quality and was more intelligible compared with three and five layers. |
| Author | Wu, Xiaojun AL-Taai, Raghad Yaseen Lazim |
| Author_xml | – sequence: 1 givenname: Raghad Yaseen Lazim surname: AL-Taai fullname: AL-Taai, Raghad Yaseen Lazim – sequence: 2 givenname: Xiaojun surname: Wu fullname: Wu, Xiaojun |
| BookMark | eNptUE1PAjEUbAwmInLyDzTxaFZbul89IoKQkHiQ--bRfStFtl3b7oF_bwkeiPEd5s0kM_OSd0sGxhok5J6zJyEke_bHlgtWcsHZFRlOWCGSUsp0cMFvyNj7PYuTsSzN2ZB8fXSIakfnZgdGYYsm0MY6ukRw2nzSVduBdljTF_ARrYnE1B14Txf6ENB5GjUFOrNtZ_tIXxG7CMZqfyqY9sGiUbZGd0euGzh4HP_uEdks5pvZMlm_v61m03WiJrIMSamEkgVKSAvgKgOWiTpnKd8i5ygQRNM0Iq0lE3WJNWxFxnMQZclEVLgVI_Jwru2c_e7Rh2pve2fixWqS5VnBOY-VI8LPLuWs9w6bSukAQVsTHOhDxVl1-mp18dWYefyT6ZxuwR3_df8AE1R7Dg |
| CitedBy_id | crossref_primary_10_3233_JIFS_212945 |
| Cites_doi | 10.1016/j.specom.2014.06.002 10.1121/1.4948445 10.1109/TASLP.2015.2498101 10.1109/ICASSP.2017.7952121 10.1016/j.specom.2015.10.003 10.1007/978-3-319-33036-5_6 10.1109/TASSP.1980.1163421 10.21437/Interspeech.2014-222 10.1016/j.tins.2018.01.008 10.1016/j.neucom.2015.05.057 10.1016/j.specom.2011.09.002 10.1097/AUD.0000000000000537 10.21437/Interspeech.2014-574 10.1109/TBME.2016.2613960 10.1097/AUD.0b013e31824b9e21 10.1016/j.bspc.2018.09.010 |
| ContentType | Journal Article |
| Copyright | 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | AAYXX CITATION 7SC 7SR 7U5 8BQ 8FD 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO H8D HCIFZ JG9 JQ2 L6V L7M L~C L~D M7S PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS PTHSS |
| DOI | 10.3390/sym13081310 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Engineered Materials Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Aerospace Database SciTech Premium Collection Materials Research Database ProQuest Computer Science Collection ProQuest Engineering Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Engineering Database ProQuest Central Premium ProQuest One Academic ProQuest Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
| DatabaseTitle | CrossRef Publicly Available Content Database Materials Research Database Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences Aerospace Database Engineered Materials Abstracts ProQuest Engineering Collection ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace Engineering Collection Engineering Database ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection METADEX Computer and Information Systems Abstracts Professional ProQuest One Academic UKI Edition Materials Science & Engineering Collection Solid State and Superconductivity Abstracts ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | CrossRef Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Sciences (General) |
| EISSN | 2073-8994 |
| ExternalDocumentID | 10_3390_sym13081310 |
| GroupedDBID | 5VS 8FE 8FG AADQD AAYXX ABDBF ABJCF ACUHS ADBBV ADMLS AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS AMVHM BCNDV BENPR BGLVJ CCPQU CITATION E3Z ESX GX1 HCIFZ IAO ITC J9A KQ8 L6V M7S MODMG M~E OK1 PHGZM PHGZT PIMPY PQGLB PROAC PTHSS TR2 TUS 7SC 7SR 7U5 8BQ 8FD ABUWG AZQEC DWQXO H8D JG9 JQ2 L7M L~C L~D PKEHL PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c298t-8c3c97e9a47a1c5a053d6041be11e3ea3fff34d903d8edab3516a38803edaeb3 |
| IEDL.DBID | BENPR |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000690130400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2073-8994 |
| IngestDate | Fri Jul 25 11:49:52 EDT 2025 Tue Nov 18 21:51:05 EST 2025 Sat Nov 29 07:16:29 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c298t-8c3c97e9a47a1c5a053d6041be11e3ea3fff34d903d8edab3516a38803edaeb3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://www.proquest.com/docview/2565711105?pq-origsite=%requestingapplication% |
| PQID | 2565711105 |
| PQPubID | 2032326 |
| ParticipantIDs | proquest_journals_2565711105 crossref_citationtrail_10_3390_sym13081310 crossref_primary_10_3390_sym13081310 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-08-01 |
| PublicationDateYYYYMMDD | 2021-08-01 |
| PublicationDate_xml | – month: 08 year: 2021 text: 2021-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Basel |
| PublicationPlace_xml | – name: Basel |
| PublicationTitle | Symmetry (Basel) |
| PublicationYear | 2021 |
| Publisher | MDPI AG |
| Publisher_xml | – name: MDPI AG |
| References | Gray (ref_8) 1980; 28 Sun (ref_13) 2016; 24 Tsao (ref_22) 2016; 76 ref_14 Lai (ref_17) 2019; 48 ref_12 ref_11 ref_19 Chen (ref_10) 2012; 54 ref_18 Kates (ref_24) 2010; 58 Kates (ref_25) 2014; 65 Lai (ref_16) 2018; 39 Seyyedsalehi (ref_21) 2015; 168 Chen (ref_5) 2016; 139 ref_20 ref_1 ref_2 ref_9 Beerends (ref_23) 2002; 50 Harbach (ref_6) 2012; 33 ref_4 Lai (ref_15) 2017; 64 ref_7 Lesica (ref_3) 2018; 41 |
| References_xml | – ident: ref_7 – ident: ref_9 – volume: 65 start-page: 75 year: 2014 ident: ref_25 article-title: The hearing-aid speech perception index (HASPI) publication-title: Speech Commun. doi: 10.1016/j.specom.2014.06.002 – ident: ref_14 – ident: ref_1 – volume: 139 start-page: 2604 year: 2016 ident: ref_5 article-title: Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises publication-title: J. Acoust. Soc. Am. doi: 10.1121/1.4948445 – volume: 24 start-page: 93 year: 2016 ident: ref_13 article-title: Unseen noise estimation using separable deep autoencoder for speech enhancement publication-title: IEEE Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2015.2498101 – ident: ref_18 doi: 10.1109/ICASSP.2017.7952121 – volume: 76 start-page: 112 year: 2016 ident: ref_22 article-title: Generalized maximum a posteriori spectral amplitude estimation for speech enhancement publication-title: Speech Commun. doi: 10.1016/j.specom.2015.10.003 – volume: 58 start-page: 363 year: 2010 ident: ref_24 article-title: The hearing-aid speech quality index (HASQI) publication-title: J. Audio Eng. Soc. – ident: ref_19 doi: 10.1007/978-3-319-33036-5_6 – volume: 28 start-page: 367 year: 1980 ident: ref_8 article-title: Distortion measures for speech processing publication-title: IEEE Trans. Acoust. Speech Signal Process. doi: 10.1109/TASSP.1980.1163421 – ident: ref_12 doi: 10.21437/Interspeech.2014-222 – ident: ref_4 – volume: 50 start-page: 765 year: 2002 ident: ref_23 article-title: Perceptual evaluation of speech quality (PESQ) the new ITU standard for end-to-end speech quality assessment part 2: Psychoacoustic model publication-title: J. Audio Eng. Soc. – ident: ref_2 – volume: 41 start-page: 174 year: 2018 ident: ref_3 article-title: Why Do Hearing Aids Fail to Restore Normal Auditory Perception publication-title: Trends Neurosci. doi: 10.1016/j.tins.2018.01.008 – volume: 168 start-page: 669 year: 2015 ident: ref_21 article-title: A fast and efficient pre-training method based on layer-by-layer maximum discrimination for deep neural networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.05.057 – volume: 54 start-page: 81 year: 2012 ident: ref_10 article-title: Impact of SNR and gain-function over- and under-estimation on speech intelligibility publication-title: Speech Commun. doi: 10.1016/j.specom.2011.09.002 – volume: 39 start-page: 795 year: 2018 ident: ref_16 article-title: Deep Learning–Based Noise Reduction Approach to Improve Speech Intelligibility for Cochlear Implant Recipients publication-title: Ear Hear. doi: 10.1097/AUD.0000000000000537 – ident: ref_11 doi: 10.21437/Interspeech.2014-574 – volume: 64 start-page: 1568 year: 2017 ident: ref_15 article-title: A Deep Denoising Autoencoder Approach to Improving the Intelligibility of Vocoded Speech in Cochlear Implant Simulation publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2016.2613960 – volume: 33 start-page: 13 year: 2012 ident: ref_6 article-title: Combining directional microphone and single-channel noise reduction algorithms: A clinical evalua-tion in difficult listening conditions with cochlear implant users publication-title: Ear Hear. doi: 10.1097/AUD.0b013e31824b9e21 – ident: ref_20 – volume: 48 start-page: 35 year: 2019 ident: ref_17 article-title: Multi-objective learning based speech enhancement method to increase speech quality and intelligibility for hearing aid device users publication-title: Biomed. Signal Process. Control. doi: 10.1016/j.bspc.2018.09.010 |
| SSID | ssj0000505460 |
| Score | 2.2155168 |
| Snippet | Deep neural networks have been applied for speech enhancements efficiently. However, for large variations of speech patterns and noisy environments, an... |
| SourceID | proquest crossref |
| SourceType | Aggregation Database Enrichment Source Index Database |
| StartPage | 1310 |
| SubjectTerms | Algorithms Artificial neural networks Bandpass filters Frequency analysis Hearing aids Hearing loss Intelligibility Machine learning Mean square errors Noise Noise reduction Performance evaluation Signal processing Signal to noise ratio Sound Sound filters Speech Speech processing |
| Title | Speech Enhancement for Hearing Impaired Based on Bandpass Filters and a Compound Deep Denoising Autoencoder |
| URI | https://www.proquest.com/docview/2565711105 |
| Volume | 13 |
| WOSCitedRecordID | wos000690130400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2073-8994 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000505460 issn: 2073-8994 databaseCode: M~E dateStart: 20080101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 2073-8994 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000505460 issn: 2073-8994 databaseCode: M7S dateStart: 20090301 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2073-8994 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000505460 issn: 2073-8994 databaseCode: BENPR dateStart: 20090301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2073-8994 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000505460 issn: 2073-8994 databaseCode: PIMPY dateStart: 20090301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDI5gcOACjId4DJTDDoBUrW3SrT2hAZuYBNMECI1TlVe1CWjLOpC48NuxtwyGhLhwiZo2hyq2Pzu2YxNSBSYKQEtLJ9KMOdxI14mY5g4gYdLQoNP55Ib3_VWj2w37_ahnHW6FTaucYeIEqHWm0Ede8zE-B4LpBqf5i4NdozC6altoLJIlrFTGS2TprNXt3Xx5WbBPG6-704t5DM73teL9GWA79BjemZ1XRT-ReKJe2mv__bF1smoNS9qcckKZLJh0g5St6Bb0yNaXPt4kj7e5MWpAW-kASY7uQQqmK70EpgdFRjuAEACEmp6BhtM0S-Eh1TlY2bQ9xOB6QWFOBUUswa5M9MKYHIY0G6LngTZfxxnWx9RmtEXu2q2780vH9lxwlB-FYydUTEUNEwneEJ4KBMiorrvck8bzDDOCJUnCuI5cpkOjhWSBVxdYUIbBDA7m26SUZqnZIVRwIVUkle8LzQMZCgHGmZIqTMAkkZ63S05mux8rW48c22I8xXAuQVLFc6TaJdWvxfm0DMfvyyozGsVWFov4m0B7f3_eJys-ZqxM0vsqpDQevZoDsqzexsNidGhZ6xCzQ29x_GjBu17nuvfwCb2i3cc |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1La9tAEB5Su9Be2qZtaNqk2YMLTUFE0q5s7SGUpImxsWMMMSU9iX2JmCSSYjkt-VH9j5mxpTSF0psPuQgtWoSk_fTNY-cB0EIQRSiltSct555w2vckt8JDJkw7FmW6WGR4fx92RqP47EyO1-B3nQtDYZU1Jy6I2uaGfOR7Ie3P4Y_pR1-La4-6RtHuat1CYwmLgbv9hSZbud8_wvX9FIbd48m3nld1FfBMKOO5FxtuZMdJJToqMJFCFNq2LwLtgsBxp3iaplxY6XMbO6s0j4K2opIpHEdoeuJtn0BTINbjBjTH_ZPxj3unDrWFE21_mQfIufT3ytsrlBJxwClF96Hk-5v4F9Ks-_KRfYdX8KJSm9nBEufrsOay17BeEVPJPlfVs3ffwMVp4Zw5Z8fZOQGanJ8MFXPWw2dGMc36yH9I85Ydovy2LM_wJLMF2hCsO6XQgZLhmClGTEk9p9iRcwUesnxKfhV2cDPPqfqndbO3MFnFO29AI8sz9w6YEkobqU0YKisiHSuFqqfRJk5R4dJBsAlf6sVOTFVtnZp-XCZodREykgfI2ITW_eRiWWTk39O2akgkFdOUyR88vP__5R141pucDJNhfzT4AM9Dis1ZBDJuQWM-u3Hb8NT8nE_L2ccK1QySFePnDoxTOEo |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bS9xAFD6oLeKL1mrx1joPFqoQNslMNpkHKdp1cVEWQSm-hbkFl2oSN6viT-u_6znZxAuUvvnQl5AhQ0gyX853zplzAdhBEEXI0tqTlnNPOO17klvhoSTMYoucLuoM75-n8XCYXF7Ksxn43ebCUFhlKxNrQW0LQz7yTkj7c_hj-lEna8Iiznr97-WtRx2kaKe1bacxhciJe3xA863aH_Rwrb-GYf_o4sex13QY8Ewok4mXGG5k7KQSsQpMpBCRtuuLQLsgcNwpnmUZF1b63CbOKs2joKuofArHEZqheNtZeBcLVBPqqMHzJ_cONYgTXX-aEci59DvV4w3yRRJwStZ9yYGvKaDmtf7Sf_xFPsBio0yzgyn6l2HG5R9huRFXFfvW1NTeXYFf56Vz5ood5VcEc3KJMlTX2TE-M5I3G6BUROFv2SGyumVFjie5LdGyYP0RBRRUDMdMMZKf1ImK9Zwr8ZAXI_K2sIO7SUE1Qa0br8LFW7zzJ5jLi9ytAVNCaSO1CUNlRaQTpVAhNdokGaphOgjWYa9d-NQ0NdipFch1irYYoSR9gZJ12HmaXE5Lj_x92lYLj7SRP1X6jI2Nf1_ehnkETXo6GJ5swkJIATt1dOMWzE3Gd-4zvDf3k1E1_lLDm0H6xuD5A-kZP5E |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Speech+Enhancement+for+Hearing+Impaired+Based+on+Bandpass+Filters+and+a+Compound+Deep+Denoising+Autoencoder&rft.jtitle=Symmetry+%28Basel%29&rft.au=AL-Taai%2C+Raghad+Yaseen+Lazim&rft.au=Wu%2C+Xiaojun&rft.date=2021-08-01&rft.issn=2073-8994&rft.eissn=2073-8994&rft.volume=13&rft.issue=8&rft.spage=1310&rft_id=info:doi/10.3390%2Fsym13081310&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_sym13081310 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2073-8994&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2073-8994&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2073-8994&client=summon |