Amazigh speech recognition based on the Kaldi ASR toolkit

In this work, we offer a new approach to integrating the Amazigh language, which is a less-resourced language, into an isolated speech recognition system by exploiting the Kaldi open-source platform. Our designed system is able to recognize the ten first Amazigh digits and ten daily must-used Amazig...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of information technology (Singapore. Online) Vol. 15; no. 7; pp. 3533 - 3540
Main Authors Barkani, Fatima, Hamidi, Mohamed, Laaidi, Naouar, Zealouk, Ouissam, Satori, Hassan, Satori, Khalid
Format Journal Article
LanguageEnglish
Published Singapore Springer Nature Singapore 01.10.2023
Subjects
Artificial Intelligence
Computer Imaging
Computer Science
Image Processing and Computer Vision
Machine Learning
Original Research
Pattern Recognition and Graphics
Software Engineering
Vision
Amazigh language
Kaldi
PLP
GMM
Speech recognition
CMU Sphinx4
HMM
FBANK
MFCC
Online AccessGet full text

Cover

Abstract In this work, we offer a new approach to integrating the Amazigh language, which is a less-resourced language, into an isolated speech recognition system by exploiting the Kaldi open-source platform. Our designed system is able to recognize the ten first Amazigh digits and ten daily must-used Amazigh isolated words, which present typical syllabic structure and which are considered a good representative sample of the Amazigh language. The designed speech system was implemented using Hidden Markov Models (HMMs) with different number of Gaussian distributions. In addition, we evaluated our created system performance by varying the feature extraction methods in order to determine the optimal method for maximum performance. The best-obtained result is 93.96% was obtained with Mel Frequency Cepstral Coefficients (MFCCs) technique.
AbstractList In this work, we offer a new approach to integrating the Amazigh language, which is a less-resourced language, into an isolated speech recognition system by exploiting the Kaldi open-source platform. Our designed system is able to recognize the ten first Amazigh digits and ten daily must-used Amazigh isolated words, which present typical syllabic structure and which are considered a good representative sample of the Amazigh language. The designed speech system was implemented using Hidden Markov Models (HMMs) with different number of Gaussian distributions. In addition, we evaluated our created system performance by varying the feature extraction methods in order to determine the optimal method for maximum performance. The best-obtained result is 93.96% was obtained with Mel Frequency Cepstral Coefficients (MFCCs) technique.
Author Barkani, Fatima
Satori, Hassan
Laaidi, Naouar
Zealouk, Ouissam
Satori, Khalid
Hamidi, Mohamed
Author_xml – sequence: 1
  givenname: Fatima
  surname: Barkani
  fullname: Barkani, Fatima
  organization: Laboratory of Computer Science, Signals, Automation and Cognitivism, Faculty of Sciences Dhar Mahraz, University Sidi Mohamed Ben Abdellah
– sequence: 2
  givenname: Mohamed
  orcidid: 0000-0003-2487-5517
  surname: Hamidi
  fullname: Hamidi, Mohamed
  email: mohamed.hamidi.5@gmail.com
  organization: Team of modeling and scientific computing, Pluridisciplinary Faculty of Nador, Mohammed First University
– sequence: 3
  givenname: Naouar
  surname: Laaidi
  fullname: Laaidi, Naouar
  organization: Laboratory of Computer Science, Signals, Automation and Cognitivism, Faculty of Sciences Dhar Mahraz, University Sidi Mohamed Ben Abdellah
– sequence: 4
  givenname: Ouissam
  surname: Zealouk
  fullname: Zealouk, Ouissam
  organization: Laboratory of Computer Science, Signals, Automation and Cognitivism, Faculty of Sciences Dhar Mahraz, University Sidi Mohamed Ben Abdellah
– sequence: 5
  givenname: Hassan
  surname: Satori
  fullname: Satori, Hassan
  organization: Laboratory of Computer Science, Signals, Automation and Cognitivism, Faculty of Sciences Dhar Mahraz, University Sidi Mohamed Ben Abdellah
– sequence: 6
  givenname: Khalid
  surname: Satori
  fullname: Satori, Khalid
  organization: Laboratory of Computer Science, Signals, Automation and Cognitivism, Faculty of Sciences Dhar Mahraz, University Sidi Mohamed Ben Abdellah
BookMark eNp9j8tOwzAQRS0EEqX0B1j5BwwzftTxsqp4iUpIPNaW4zitoY0rOyzI1xMoYslq7mLO1T1n5LhLXSDkAuESAfRVkVhpYMAFAxRKsuGITLhCZByRH_9lkKdkVkqsQSCfC6VxQsxi54a43tCyD8FvaA4-rbvYx9TR2pXQ0DH0m0Af3LaJdPH8RPuUtu-xPycnrduWMPu9U_J6c_2yvGOrx9v75WLFPBdyYMZUAhWAEFJ6WUHTOi7EXDsUvvK6kUaCb2vTgDJOa15rL1QdnJKoTVu3Ykr4odfnVEoOrd3nuHP50yLYb3978Lejv_3xt8MIiQNUxuduHbJ9Sx-5G3f-R30B7EJemg
CitedBy_id crossref_primary_10_1007_s10772_023_10054_9
Cites_doi 10.1214/aoms/1177699147
10.1007/978-3-319-43958-7_13
10.1121/1.399423
10.1007/978-981-15-0947-6_26
10.1007/978-3-319-74500-8_37
10.1007/978-3-319-24033-6_54
10.1023/A:1007469218079
10.1007/s10772-021-09847-7
10.1007/s10772-014-9223-y
10.1007/s10772-019-09661-2
10.1016/j.procs.2018.01.102
10.1109/MASSP.1986.1165342
10.1109/TASSP.1980.1163420
10.1007/s10772-017-9442-0
10.1007/s41870-020-00552-3
10.1007/s10772-020-09764-1
10.1109/EMS.2016.018
10.1109/ISCV49265.2020.9204250
10.1109/ICDS50568.2020.9268765
10.1109/ICACCI.2017.8126111
10.1109/WorldS4.2018.8611591
10.1109/IRASET48871.2020.9092014
10.1109/ECACE.2019.8679341
10.21437/Eurospeech.1999-531x
ContentType Journal Article
Copyright The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Copyright_xml – notice: The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
DBID AAYXX
CITATION
DOI 10.1007/s41870-023-01354-z
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 2511-2112
EndPage 3540
ExternalDocumentID 10_1007_s41870_023_01354_z
GroupedDBID -EM
406
AAFGU
AAHNG
AAIAL
AANZL
AAPBV
AATNV
AATVU
AAUYE
AAYFA
ABDZT
ABECU
ABFGW
ABFTV
ABJNI
ABJOX
ABKAS
ABKCH
ABMQK
ABQBU
ABTEG
ABTKH
ABTMW
ABXPI
ACBMV
ACBRV
ACBYP
ACGFS
ACHSB
ACIGE
ACIPQ
ACMLO
ACOKC
ACTTH
ACVWB
ACWMK
ADHHG
ADKNI
ADKPE
ADMDM
ADOXG
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFTE
AEJRE
AEOHA
AESKC
AESTI
AEVLU
AEVTX
AEXYK
AFNRJ
AFQWF
AGDGC
AGGBP
AGMZJ
AHSBF
AIAKS
AILAN
AIMYW
AITGF
AJDOV
AJRNO
AJZVZ
AKQUC
ALFXC
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMXSW
AMYLF
AMYQR
AXYYD
BGNMA
CSCUP
DNIVK
DPUIP
EBLON
EBS
EIOEI
EJD
FERAY
FINBP
FNLPD
FSGXE
GGCAI
GJIRD
IKXTQ
IWAJR
J-C
JZLTJ
KOV
LLZTM
M4Y
NPVJJ
NQJWS
NU0
O9J
PT4
RLLFE
RSV
SISQX
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
TSG
UOJIU
UTJUX
UZXMN
VFIZW
Z7R
Z7X
Z7Z
Z81
Z83
Z88
ZMTXR
0R~
AACDK
AAJBT
AASML
AAYXX
ABAKF
ACAOD
ACDTI
ACZOJ
AEFQL
AEMSY
AFBBN
AGQEE
AGRTI
AIGIU
CITATION
FIGPU
ROL
SJYHP
ID FETCH-LOGICAL-c234z-998315003344c480dfa23367a13c8c7d4940cfb9d059a772b7c35bea54179fbf3
ISSN 2511-2104
IngestDate Wed Oct 23 14:32:23 EDT 2024
Sat Dec 16 12:03:34 EST 2023
IsPeerReviewed false
IsScholarly true
Issue 7
Keywords Amazigh language
Kaldi
PLP
GMM
Speech recognition
CMU Sphinx4
HMM
FBANK
MFCC
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c234z-998315003344c480dfa23367a13c8c7d4940cfb9d059a772b7c35bea54179fbf3
ORCID 0000-0003-2487-5517
PageCount 8
ParticipantIDs crossref_primary_10_1007_s41870_023_01354_z
springer_journals_10_1007_s41870_023_01354_z
PublicationCentury 2000
PublicationDate 2023-10-01
PublicationDateYYYYMMDD 2023-10-01
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-10-01
  day: 01
PublicationDecade 2020
PublicationPlace Singapore
PublicationPlace_xml – name: Singapore
PublicationSubtitle An Official Journal of Bharati Vidyapeeth's Institute of Computer Applications and Management
PublicationTitle International journal of information technology (Singapore. Online)
PublicationTitleAbbrev Int. j. inf. tecnol
PublicationYear 2023
Publisher Springer Nature Singapore
Publisher_xml – name: Springer Nature Singapore
References Këpuska, Bohouta (CR8) 2017; 7
CR19
Medennikov, Prudnikov (CR13) 2016
CR39
CR38
CR15
CR37
Hamidi, Satori, Zealouk, Satori (CR23) 2019; 11
CR35
Hamidi, Zealouk, Satori, Laaidi, Salek (CR1) 2022; 15
CR12
Satori, Elhaoussi (CR18) 2014; 17
Satori, Zealouk, Satori, Elhaoussi (CR22) 2017; 20
CR11
CR33
Hamidi, Satori, Zealouk, Satori (CR20) 2020; 23
Telmem, Ghanou (CR25) 2018; 127
Davis, Mermelstein (CR32) 1980; 28
Hamidi, Satori, Zealouk, Satori (CR24) 2020
Saady, Rachidi, Yassa, Mammass (CR17) 2011; 27
Ouisaadane, Safi (CR36) 2021; 24
Ameen, Kadhim (CR16) 2023; 13
Hasan, Dhawan, Rizvi, Dhir (CR3) 2022
Telmem, Ghanou (CR26) 2021; 19
Alafif, Etaiwi, Hawsawi, Alrefaei, Albassam, Althobaiti (CR4) 2022; 14
CR6
CR5
CR7
Beal, Ghahramani, Rasmussen (CR31) 2001; 14
CR9
Zealouk, Satori, Laaidi, Hamidi, Satori (CR10) 2020; 23
Baum, Petrie (CR28) 1966; 37
Fine, Singer, Tishby (CR30) 1998; 32
CR21
Rabiner, Juang (CR29) 1986; 3
Radeck-Arneth, Milde, Lange, Gouvêa, Radomski, Mühlhäuser, Biemann (CR40) 2015
Telmem, Ghanou (CR27) 2018
Hermansky (CR34) 1990; 87
Senapati, Nag, Mondal, Maji (CR2) 2021; 13
Zealouk, Satori, Hamidi, Satori (CR14) 2019; 11
A Senapati (1354_CR2) 2021; 13
M Hamidi (1354_CR20) 2020; 23
L Rabiner (1354_CR29) 1986; 3
S Fine (1354_CR30) 1998; 32
H Hermansky (1354_CR34) 1990; 87
YE Saady (1354_CR17) 2011; 27
M Hamidi (1354_CR24) 2020
1354_CR6
1354_CR5
1354_CR21
M Telmem (1354_CR25) 2018; 127
M Hamidi (1354_CR23) 2019; 11
I Hasan (1354_CR3) 2022
1354_CR7
A Ouisaadane (1354_CR36) 2021; 24
ZJM Ameen (1354_CR16) 2023; 13
M Beal (1354_CR31) 2001; 14
1354_CR9
S Davis (1354_CR32) 1980; 28
O Zealouk (1354_CR14) 2019; 11
1354_CR19
M Hamidi (1354_CR1) 2022; 15
T Alafif (1354_CR4) 2022; 14
1354_CR15
1354_CR37
1354_CR39
1354_CR38
I Medennikov (1354_CR13) 2016
H Satori (1354_CR18) 2014; 17
M Telmem (1354_CR27) 2018
V Këpuska (1354_CR8) 2017; 7
O Zealouk (1354_CR10) 2020; 23
H Satori (1354_CR22) 2017; 20
1354_CR11
1354_CR33
M Telmem (1354_CR26) 2021; 19
1354_CR35
1354_CR12
S Radeck-Arneth (1354_CR40) 2015
LE Baum (1354_CR28) 1966; 37
References_xml – volume: 37
  start-page: 1554
  issue: 6
  year: 1966
  end-page: 1563
  ident: CR28
  article-title: Statistical inference for probabilistic functions of finite state Markov chains
  publication-title: Ann Math Stat
  doi: 10.1214/aoms/1177699147
  contributor:
    fullname: Petrie
– start-page: 116
  year: 2016
  end-page: 123
  ident: CR13
  article-title: Advances in STC Russian spontaneous speech recognition system
  publication-title: International conference on speech and computer
  doi: 10.1007/978-3-319-43958-7_13
  contributor:
    fullname: Prudnikov
– ident: CR39
– ident: CR37
– volume: 7
  start-page: 20
  issue: 03
  year: 2017
  end-page: 24
  ident: CR8
  article-title: Comparing speech recognition systems (Microsoft API, Google API and CMU Sphinx)
  publication-title: Int J Eng Res Appl
  contributor:
    fullname: Bohouta
– volume: 87
  start-page: 1738
  issue: 4
  year: 1990
  end-page: 1752
  ident: CR34
  article-title: Perceptual linear predictive (PLP) analysis of speech
  publication-title: J Acoust Soc Am
  doi: 10.1121/1.399423
  contributor:
    fullname: Hermansky
– ident: CR12
– start-page: 271
  year: 2020
  end-page: 279
  ident: CR24
  article-title: Interactive voice application-based Amazigh speech recognition
  publication-title: Embedded systems and artificial intelligence
  doi: 10.1007/978-981-15-0947-6_26
  contributor:
    fullname: Satori
– start-page: 397
  year: 2018
  end-page: 410
  ident: CR27
  article-title: Amazigh speech recognition system based on CMUSphinx
  publication-title: Innovations in smart cities and applications: proceedings of the 2nd Mediterranean symposium on smart city applications
  doi: 10.1007/978-3-319-74500-8_37
  contributor:
    fullname: Ghanou
– ident: CR33
– start-page: 480
  year: 2015
  end-page: 488
  ident: CR40
  article-title: Open source German distant speech recognition: corpus and acoustic model
  publication-title: International conference on text, speech, and dialogue
  doi: 10.1007/978-3-319-24033-6_54
  contributor:
    fullname: Biemann
– volume: 27
  start-page: 44
  issue: 4
  year: 2011
  end-page: 48
  ident: CR17
  article-title: Amhcd: a database for amazigh handwritten character recognition research
  publication-title: Int J Comput Appl
  contributor:
    fullname: Mammass
– ident: CR35
– volume: 13
  start-page: 41
  issue: 1
  year: 2021
  end-page: 48
  ident: CR2
  article-title: A novel framework for COVID-19 case prediction through piecewise regression in India
  publication-title: Int J Inf Technol
  contributor:
    fullname: Maji
– ident: CR6
– volume: 32
  start-page: 41
  issue: 1
  year: 1998
  end-page: 62
  ident: CR30
  article-title: The hierarchical hidden Markov model: analysis and applications
  publication-title: Mach Learn
  doi: 10.1023/A:1007469218079
  contributor:
    fullname: Tishby
– volume: 14
  start-page: 577
  year: 2001
  end-page: 584
  ident: CR31
  article-title: The infinite hidden Markov model
  publication-title: Adv Neural Inf Process Syst
  contributor:
    fullname: Rasmussen
– volume: 24
  start-page: 761
  issue: 3
  year: 2021
  end-page: 770
  ident: CR36
  article-title: A comparative study for Arabic speech recognition system in noisy environments
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-021-09847-7
  contributor:
    fullname: Safi
– volume: 17
  start-page: 235
  issue: 3
  year: 2014
  end-page: 243
  ident: CR18
  article-title: Investigation Amazigh speech recognition using CMU tools
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-014-9223-y
  contributor:
    fullname: Elhaoussi
– ident: CR21
– ident: CR19
– volume: 23
  start-page: 101
  issue: 1
  year: 2020
  end-page: 109
  ident: CR20
  article-title: Amazigh digits through interactive speech recognition system in noisy environment
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-019-09661-2
  contributor:
    fullname: Satori
– ident: CR15
– volume: 127
  start-page: 92
  year: 2018
  end-page: 101
  ident: CR25
  article-title: Estimation of the optimal HMM parameters for Amazigh speech recognition system using CMU-Sphinx
  publication-title: Proced Comput Sci
  doi: 10.1016/j.procs.2018.01.102
  contributor:
    fullname: Ghanou
– ident: CR38
– volume: 14
  start-page: 2825
  issue: 6
  year: 2022
  end-page: 2838
  ident: CR4
  article-title: DISCOVID: discovering patterns of COVID-19 infection from recovered patients: a case study in Saudi Arabia
  publication-title: Int J Inf Technol
  contributor:
    fullname: Althobaiti
– volume: 11
  start-page: 1392
  issue: 2
  year: 2019
  end-page: 1400
  ident: CR23
  article-title: Speech coding effect on Amazigh alphabet speech recognition performance
  publication-title: J Adv Res Dyn Control Syst
  contributor:
    fullname: Satori
– ident: CR11
– ident: CR9
– volume: 19
  start-page: 515
  issue: 2
  year: 2021
  end-page: 522
  ident: CR26
  article-title: The convolutional neural networks for Amazigh speech recognition system
  publication-title: Telecommun Comput Electron Control
  contributor:
    fullname: Ghanou
– volume: 3
  start-page: 4
  issue: 1
  year: 1986
  end-page: 16
  ident: CR29
  article-title: An introduction to hidden Markov models
  publication-title: IEEE ASSP Mag
  doi: 10.1109/MASSP.1986.1165342
  contributor:
    fullname: Juang
– volume: 28
  start-page: 357
  issue: 4
  year: 1980
  end-page: 366
  ident: CR32
  article-title: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences
  publication-title: IEEE Trans Acoust Speech Signal Process
  doi: 10.1109/TASSP.1980.1163420
  contributor:
    fullname: Mermelstein
– volume: 20
  start-page: 771
  issue: 4
  year: 2017
  end-page: 777
  ident: CR22
  article-title: Voice comparison between smokers and non-smokers using HMM speech recognition system
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-017-9442-0
  contributor:
    fullname: Elhaoussi
– ident: CR5
– ident: CR7
– volume: 11
  start-page: 1401
  issue: 2
  year: 2019
  end-page: 1408
  ident: CR14
  article-title: Speech recognition for Moroccan dialects: feature extraction and classification methods
  publication-title: J Adv Res Dyn Control Syst
  contributor:
    fullname: Satori
– volume: 15
  start-page: 193
  year: 2022
  end-page: 201
  ident: CR1
  article-title: COVID-19 assessment using HMM cough recognition system
  publication-title: Int J Inf Technol
  contributor:
    fullname: Salek
– year: 2022
  ident: CR3
  article-title: Data analytics and knowledge management approach for COVID-19 prediction and control
  publication-title: Int J Inf Technol
  doi: 10.1007/s41870-020-00552-3
  contributor:
    fullname: Dhir
– volume: 23
  start-page: 885
  issue: 4
  year: 2020
  end-page: 892
  ident: CR10
  article-title: Noise effect on Amazigh digits in speech recognition system
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-020-09764-1
  contributor:
    fullname: Satori
– volume: 13
  start-page: 400
  issue: 1
  year: 2023
  ident: CR16
  article-title: Machine learning for Arabic phonemes recognition using electrolarynx speech
  publication-title: Int J Electr Comput Eng
  contributor:
    fullname: Kadhim
– volume: 27
  start-page: 44
  issue: 4
  year: 2011
  ident: 1354_CR17
  publication-title: Int J Comput Appl
  contributor:
    fullname: YE Saady
– start-page: 271
  volume-title: Embedded systems and artificial intelligence
  year: 2020
  ident: 1354_CR24
  doi: 10.1007/978-981-15-0947-6_26
  contributor:
    fullname: M Hamidi
– volume: 28
  start-page: 357
  issue: 4
  year: 1980
  ident: 1354_CR32
  publication-title: IEEE Trans Acoust Speech Signal Process
  doi: 10.1109/TASSP.1980.1163420
  contributor:
    fullname: S Davis
– ident: 1354_CR35
  doi: 10.1109/EMS.2016.018
– volume: 14
  start-page: 2825
  issue: 6
  year: 2022
  ident: 1354_CR4
  publication-title: Int J Inf Technol
  contributor:
    fullname: T Alafif
– volume: 37
  start-page: 1554
  issue: 6
  year: 1966
  ident: 1354_CR28
  publication-title: Ann Math Stat
  doi: 10.1214/aoms/1177699147
  contributor:
    fullname: LE Baum
– volume: 13
  start-page: 41
  issue: 1
  year: 2021
  ident: 1354_CR2
  publication-title: Int J Inf Technol
  contributor:
    fullname: A Senapati
– start-page: 116
  volume-title: International conference on speech and computer
  year: 2016
  ident: 1354_CR13
  doi: 10.1007/978-3-319-43958-7_13
  contributor:
    fullname: I Medennikov
– volume: 20
  start-page: 771
  issue: 4
  year: 2017
  ident: 1354_CR22
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-017-9442-0
  contributor:
    fullname: H Satori
– volume: 7
  start-page: 20
  issue: 03
  year: 2017
  ident: 1354_CR8
  publication-title: Int J Eng Res Appl
  contributor:
    fullname: V Këpuska
– ident: 1354_CR15
  doi: 10.1109/ISCV49265.2020.9204250
– start-page: 397
  volume-title: Innovations in smart cities and applications: proceedings of the 2nd Mediterranean symposium on smart city applications
  year: 2018
  ident: 1354_CR27
  doi: 10.1007/978-3-319-74500-8_37
  contributor:
    fullname: M Telmem
– ident: 1354_CR5
  doi: 10.1109/ICDS50568.2020.9268765
– volume: 13
  start-page: 400
  issue: 1
  year: 2023
  ident: 1354_CR16
  publication-title: Int J Electr Comput Eng
  contributor:
    fullname: ZJM Ameen
– ident: 1354_CR39
– volume: 3
  start-page: 4
  issue: 1
  year: 1986
  ident: 1354_CR29
  publication-title: IEEE ASSP Mag
  doi: 10.1109/MASSP.1986.1165342
  contributor:
    fullname: L Rabiner
– volume: 87
  start-page: 1738
  issue: 4
  year: 1990
  ident: 1354_CR34
  publication-title: J Acoust Soc Am
  doi: 10.1121/1.399423
  contributor:
    fullname: H Hermansky
– volume: 11
  start-page: 1401
  issue: 2
  year: 2019
  ident: 1354_CR14
  publication-title: J Adv Res Dyn Control Syst
  contributor:
    fullname: O Zealouk
– volume: 14
  start-page: 577
  year: 2001
  ident: 1354_CR31
  publication-title: Adv Neural Inf Process Syst
  contributor:
    fullname: M Beal
– volume: 11
  start-page: 1392
  issue: 2
  year: 2019
  ident: 1354_CR23
  publication-title: J Adv Res Dyn Control Syst
  contributor:
    fullname: M Hamidi
– volume: 19
  start-page: 515
  issue: 2
  year: 2021
  ident: 1354_CR26
  publication-title: Telecommun Comput Electron Control
  contributor:
    fullname: M Telmem
– ident: 1354_CR33
– ident: 1354_CR6
– year: 2022
  ident: 1354_CR3
  publication-title: Int J Inf Technol
  doi: 10.1007/s41870-020-00552-3
  contributor:
    fullname: I Hasan
– volume: 15
  start-page: 193
  year: 2022
  ident: 1354_CR1
  publication-title: Int J Inf Technol
  contributor:
    fullname: M Hamidi
– volume: 17
  start-page: 235
  issue: 3
  year: 2014
  ident: 1354_CR18
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-014-9223-y
  contributor:
    fullname: H Satori
– volume: 127
  start-page: 92
  year: 2018
  ident: 1354_CR25
  publication-title: Proced Comput Sci
  doi: 10.1016/j.procs.2018.01.102
  contributor:
    fullname: M Telmem
– start-page: 480
  volume-title: International conference on text, speech, and dialogue
  year: 2015
  ident: 1354_CR40
  doi: 10.1007/978-3-319-24033-6_54
  contributor:
    fullname: S Radeck-Arneth
– ident: 1354_CR12
  doi: 10.1109/ICACCI.2017.8126111
– ident: 1354_CR11
– ident: 1354_CR19
  doi: 10.1109/WorldS4.2018.8611591
– volume: 32
  start-page: 41
  issue: 1
  year: 1998
  ident: 1354_CR30
  publication-title: Mach Learn
  doi: 10.1023/A:1007469218079
  contributor:
    fullname: S Fine
– ident: 1354_CR38
– volume: 23
  start-page: 101
  issue: 1
  year: 2020
  ident: 1354_CR20
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-019-09661-2
  contributor:
    fullname: M Hamidi
– ident: 1354_CR21
  doi: 10.1109/IRASET48871.2020.9092014
– ident: 1354_CR37
  doi: 10.1109/ECACE.2019.8679341
– volume: 24
  start-page: 761
  issue: 3
  year: 2021
  ident: 1354_CR36
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-021-09847-7
  contributor:
    fullname: A Ouisaadane
– volume: 23
  start-page: 885
  issue: 4
  year: 2020
  ident: 1354_CR10
  publication-title: Int J Speech Technol
  doi: 10.1007/s10772-020-09764-1
  contributor:
    fullname: O Zealouk
– ident: 1354_CR9
– ident: 1354_CR7
  doi: 10.21437/Eurospeech.1999-531x
SSID ssib031263571
ssj0002710285
Score 2.28794
Snippet In this work, we offer a new approach to integrating the Amazigh language, which is a less-resourced language, into an isolated speech recognition system by...
SourceID crossref
springer
SourceType Aggregation Database
Publisher
StartPage 3533
SubjectTerms Artificial Intelligence
Computer Imaging
Computer Science
Image Processing and Computer Vision
Machine Learning
Original Research
Pattern Recognition and Graphics
Software Engineering
Vision
Title Amazigh speech recognition based on the Kaldi ASR toolkit
URI https://link.springer.com/article/10.1007/s41870-023-01354-z
Volume 15
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9NAEF6F9gKHUgqIlof2wM24ir3rODmmiCgCNUi0lXqzxvtQQ5s4auKLf1R_Y2fXm7WtFkS5WNZmYtmez_PaeRDyOeYqlajHQ-iLQchBM_zmIham0jbFHaSRDeaczgbTC_79Mrns9e5aWUvlJj8W1aN1Jf_DVVxDvpoq2Sdw1l8UF_Ac-YtH5DAe_4nH4wVU6FwH65VS4irwyUDIUaOdpNsJCH7AjZwH47NfaGkWN9fzTjy-GxPsdJLwlY3BxkfgjUl6ZuZor0z_y6DdqtSFRG-v6zlRwQT_24j9KSzm0q6fFlewcEVVtucjuB9mUJTgs4VN2mVRWmn9s0R8wKIdooibZLduiNLkX5tdEX-Tjawzjk4Yu0nEx6q9FnWFddICZdqSvCypG2o4LW7CWY9qiDopZM2joZm4E5tkMqQNq0Yf-ixF39HZEmdInFnirHpGdmMUbChRd8eTk5PZVoKxyPT2cQb2b7utaww4k0frn9BVbtn6zQd30bWOulvz1uI53yd7zlWh4xp3r0hPLQ_Iy-0YEOq0wgF50epp-ZqMHChpDUraAiW1oKR4gqCkFpQUQUkdKN-Qi8m386_T0M3nCEXMeBWip87Qn-gzxrngw77UEDM2SCFiYihSyUe8L3Q-kmjCA3pxeSpYkitIzNQ7nWv2luwsi6V6RyigYZmPNL4qvDIomceaQYTGpUgEi7Q-JMH2vWSrug1L9mf2HJIv21eXuc9m_Rfyo6eRvyfPG5B_IDub21J9RMt0k39ycLgH2E-HMQ
link.rule.ids 315,783,787,27936,27937
linkProvider Library Specific Holdings
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=Amazigh+speech+recognition+based+on+the+Kaldi+ASR+toolkit&rft.jtitle=International+journal+of+information+technology+%28Singapore.+Online%29&rft.au=Barkani%2C+Fatima&rft.au=Hamidi%2C+Mohamed&rft.au=Laaidi%2C+Naouar&rft.au=Zealouk%2C+Ouissam&rft.date=2023-10-01&rft.pub=Springer+Nature+Singapore&rft.issn=2511-2104&rft.eissn=2511-2112&rft.volume=15&rft.issue=7&rft.spage=3533&rft.epage=3540&rft_id=info:doi/10.1007%2Fs41870-023-01354-z&rft.externalDocID=10_1007_s41870_023_01354_z
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2511-2104&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2511-2104&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2511-2104&client=summon