A Comparative Analysis of Various Deep-Learning Models for Noise Suppression

Excessive noise in speech communication systems is a major issue affecting various fields, including teleconferencing and hearing aid systems. To tackle this issue, various deep-learning models have been proposed, with autoencoder-based models showing remarkable results. In this paper, we present a...

Full description

Saved in:
Bibliographic Details
Published inEAI endorsed transactions on internet of things Vol. 10
Main Authors Gajjar, Henil, Selarka, Trushti, Lakdawala, Absar M., Shah, Dhaval B., Kapil, P. N.
Format Journal Article
LanguageEnglish
Published 2024
Online AccessGet full text

Cover

Loading…
Abstract Excessive noise in speech communication systems is a major issue affecting various fields, including teleconferencing and hearing aid systems. To tackle this issue, various deep-learning models have been proposed, with autoencoder-based models showing remarkable results. In this paper, we present a comparative analysis of four different deep learning based autoencoder models, namely model ‘alpha’, model ‘beta’, model ‘gamma’, and model ‘delta’ for noise suppression in speech signals. The performance of each model was evaluated using objective metric, mean squared error (MSE). Our experimental results showed that the model ‘alpha’ outperformed the other models, achieving a minimum error of 0.0086 and maximum error of 0.0158. The model ‘gamma’ also performed well, with a minimum error of 0.0169 and maximum error of 0.0216. These findings suggest that the pro-posed models have great potential for enhancing speech communication systems in various fields.
AbstractList Excessive noise in speech communication systems is a major issue affecting various fields, including teleconferencing and hearing aid systems. To tackle this issue, various deep-learning models have been proposed, with autoencoder-based models showing remarkable results. In this paper, we present a comparative analysis of four different deep learning based autoencoder models, namely model ‘alpha’, model ‘beta’, model ‘gamma’, and model ‘delta’ for noise suppression in speech signals. The performance of each model was evaluated using objective metric, mean squared error (MSE). Our experimental results showed that the model ‘alpha’ outperformed the other models, achieving a minimum error of 0.0086 and maximum error of 0.0158. The model ‘gamma’ also performed well, with a minimum error of 0.0169 and maximum error of 0.0216. These findings suggest that the pro-posed models have great potential for enhancing speech communication systems in various fields.
Author Lakdawala, Absar M.
Shah, Dhaval B.
Gajjar, Henil
Kapil, P. N.
Selarka, Trushti
Author_xml – sequence: 1
  givenname: Henil
  surname: Gajjar
  fullname: Gajjar, Henil
– sequence: 2
  givenname: Trushti
  surname: Selarka
  fullname: Selarka, Trushti
– sequence: 3
  givenname: Absar M.
  surname: Lakdawala
  fullname: Lakdawala, Absar M.
– sequence: 4
  givenname: Dhaval B.
  surname: Shah
  fullname: Shah, Dhaval B.
– sequence: 5
  givenname: P. N.
  surname: Kapil
  fullname: Kapil, P. N.
BookMark eNpN0DtPwzAUBWALFYlSOvEHvKMUv-LEYxSeUoCBxxo5yTUySu3IN0Xqv4eqDEzn6Axn-M7JIsQAhFxytlGcldcAs4_zRuVMnJClUFxlXBqz-NfPyBrxizEmhMq1MUvSVLSO28kmO_tvoFWw4x490ujoh00-7pDeAExZAzYFHz7pUxxgROpios_RI9DX3TQlQPQxXJBTZ0eE9V-uyPvd7Vv9kDUv94911WQ9Z3rORG7koEplCm0KlQ-MGwGD6ZjhjndGqq7UihedLaV2her1oHsnNNeaSyV_1xW5Ov72KSImcO2U_NamfctZe7BojxbtwUL-AMEGU3I
Cites_doi 10.1007/978-981-99-3177-4_6
10.1109/CSNT.2015.76
10.3390/w13233470
10.1016/j.apacoust.2012.06.015
10.1109/LCOMM.2021.3091800
10.1007/s12098-017-2579-7
10.1109/ICFHR.2016.0046
10.1007/s13244-018-0639-9
10.1007/978-981-33-6881-1_4
10.1186/s13636-021-00204-9
10.1016/j.sigpro.2021.108378
10.1109/CVPRW.2014.79
10.21437/Interspeech.2018-1484
10.1103/PhysRevResearch.2.033066
10.1186/s13634-020-00707-1
10.1121/10.0005757
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.4108/eetiot.4502
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
EISSN 2414-1399
ExternalDocumentID 10_4108_eetiot_4502
GroupedDBID 8FE
8FG
AAYXX
ABDBF
ADBBV
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
BCNDV
BENPR
BGLVJ
CITATION
EN8
GROUPED_DOAJ
HCIFZ
M~E
OK1
P62
PIMPY
ID FETCH-LOGICAL-c106t-2593d4849769745d0192ed9b091f1b934b86417ba836f74c6d6cf261661343a83
ISSN 2414-1399
IngestDate Fri Dec 06 08:01:27 EST 2024
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/3.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c106t-2593d4849769745d0192ed9b091f1b934b86417ba836f74c6d6cf261661343a83
ParticipantIDs crossref_primary_10_4108_eetiot_4502
PublicationCentury 2000
PublicationDate 2024-00-00
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 2024-00-00
PublicationDecade 2020
PublicationTitle EAI endorsed transactions on internet of things
PublicationYear 2024
References 49249
49248
49259
49247
49258
49260
49246
49257
49245
49256
49244
49255
49254
49253
49252
49251
49262
49250
49261
References_xml – ident: 49259
– ident: 49260
  doi: 10.1007/978-981-99-3177-4_6
– ident: 49262
  doi: 10.1109/CSNT.2015.76
– ident: 49261
  doi: 10.3390/w13233470
– ident: 49245
  doi: 10.1016/j.apacoust.2012.06.015
– ident: 49258
  doi: 10.1109/LCOMM.2021.3091800
– ident: 49244
  doi: 10.1007/s12098-017-2579-7
– ident: 49247
  doi: 10.1109/ICFHR.2016.0046
– ident: 49246
  doi: 10.1007/s13244-018-0639-9
– ident: 49251
– ident: 49249
  doi: 10.1007/978-981-33-6881-1_4
– ident: 49257
  doi: 10.1186/s13636-021-00204-9
– ident: 49252
  doi: 10.1016/j.sigpro.2021.108378
– ident: 49250
– ident: 49248
  doi: 10.1109/CVPRW.2014.79
– ident: 49254
  doi: 10.21437/Interspeech.2018-1484
– ident: 49255
  doi: 10.1103/PhysRevResearch.2.033066
– ident: 49253
  doi: 10.1186/s13634-020-00707-1
– ident: 49256
  doi: 10.1121/10.0005757
SSID ssj0002245699
Score 2.294052
Snippet Excessive noise in speech communication systems is a major issue affecting various fields, including teleconferencing and hearing aid systems. To tackle this...
SourceID crossref
SourceType Aggregation Database
Title A Comparative Analysis of Various Deep-Learning Models for Noise Suppression
Volume 10
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8JAEN4oXrwYjRrf2YM3UkS6tOVYn2jUi2i8kX1MA0haQktM_PXO7tKyGg7qpWk2HWg7X3e_mZ0HIacChAiFbpPaVMJjCQQeZ1HgMZH4HalwkQh17vDjU9B9YfdvbWej3WSXFKIhP5fmlfxHqziGetVZsn_QbPWjOIDnqF88oobx-Csdx_ZznhfvduuLvKIJrINbrwAm3kPp_tCNz8amAEP9KRvmUNc9PW0gbPrNRR_f1SFV2TRHOlosOoqbrYWh8SFCYaMLXEf7LR-NbLx2F9JF6MYz6BggQ1J701k-KIZVFBB_V_yDj61vV-S6plCjEhtw4_K5GnB8Z_WLhuugsBnRdgZDdsA8pJh2ToQlY-UU3Fw2mzOboQCAT6g7bzRbi0Wr3Kj_sZZVEYZo22jxvhXua-FVsmaqJTp298jU_0EOafqMVrdm8zi1_Jnz5w5zcShIb5NszG0HGlsgbJEVSLfJQ0wdENASBDRL6BwE9BsIqAUBRRBQAwLqgGCHvNxc9y673rxFhifRli88NF59xSKGpBINw7bShB1URyALTM5Fx2ciCth5KHjkB0nIZKACmaDRjKzMZz6O7pJamqWwRyjjYUs2pQzbqs18EB3hy5ZAhUZJEOLF--S0fPz-xFZC6S95ywe_u-yQrGusWGfWEakV0xkcI70rxIlRzxejKFQq
link.rule.ids 314,780,784,864,4024,27923,27924,27925
linkProvider Directory of Open Access Journals
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=A+Comparative+Analysis+of+Various+Deep-Learning+Models+for+Noise+Suppression&rft.jtitle=EAI+endorsed+transactions+on+internet+of+things&rft.au=Gajjar%2C+Henil&rft.au=Selarka%2C+Trushti&rft.au=Lakdawala%2C+Absar+M.&rft.au=Shah%2C+Dhaval+B.&rft.date=2024&rft.issn=2414-1399&rft.eissn=2414-1399&rft.volume=10&rft_id=info:doi/10.4108%2Feetiot.4502&rft.externalDBID=n%2Fa&rft.externalDocID=10_4108_eetiot_4502
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2414-1399&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2414-1399&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2414-1399&client=summon