Automated ASD detection in children from raw speech using customized STFT-CNN model

Autism spectrum disorder (ASD), a prevalent neurodevelopmental condition impacting cognitive, communicative, and behavioral aspects, typically manifests in early childhood due to genetic, environmental, and immunological factors. Employing a novel dataset termed children’s ASD speech corpus (CASD-SC...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of speech technology 2024, Vol.27 (3), p.701-716
Hauptverfasser: Sai, Kurma Venkata Keerthana, Krishna, Rompicharla Thanmayee, Radha, Kodali, Rao, Dhulipalla Venkata, Muneera, Abdul
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 716
container_issue 3
container_start_page 701
container_title International journal of speech technology
container_volume 27
creator Sai, Kurma Venkata Keerthana
Krishna, Rompicharla Thanmayee
Radha, Kodali
Rao, Dhulipalla Venkata
Muneera, Abdul
description Autism spectrum disorder (ASD), a prevalent neurodevelopmental condition impacting cognitive, communicative, and behavioral aspects, typically manifests in early childhood due to genetic, environmental, and immunological factors. Employing a novel dataset termed children’s ASD speech corpus (CASD-SC), the research makes use of short-time Fourier transform (STFT) layered convolutional neural networks (CNN), incorporating an image input layer and a sequence input layer. The analysis encompasses data both with and without augmentation, exploring various CNN configurations. Results showcase that the log spectrogram-based STFT layered CNN model achieves 86.6% accuracy for the raw data, while the pre-emphasis filter (PEF) with learnables-based STFT layered CNN model attains 99.1% accuracy for the data with augmentation for detecting ASD in children. This investigation bridges the literature gap by evaluating child-specific raw speech data. The study underscores the significance of processing and training efficiency in ASD diagnosis and promotes early intervention techniques by improving ASD detection in children.
doi_str_mv 10.1007/s10772-024-10131-7
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3103963506</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3103963506</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1157-3b0f2e360e9620a27e00141cc30cb49ea04f105c122b717d0f478f78adfd2ad23</originalsourceid><addsrcrecordid>eNp9kE1PwzAMhiMEEmPwBzhF4hywk65pj9NggDSNw8Y5yvKxdVrbkbRC8OsJFIkbJ1vW-9jWQ8g1wi0CyLuIICVnwDOGgAKZPCEjnKRRgQinqRcFMp5hfk4uYtwDQClLPiKrad-1te6cpdPVPbWuc6ar2oZWDTW76mCDa6gPbU2Dfqfx6JzZ0T5WzZaaPia0-kzoaj1fs9lySevWusMlOfP6EN3Vbx2T1_nDevbEFi-Pz7PpghlMrzGxAc-dyMGVOQfNpQPADI0RYDZZ6TRkHmFikPONRGnBZ7LwstDWW64tF2NyM-w9hvatd7FT-7YPTTqpBIIoczGBPKX4kDKhjTE4r46hqnX4UAjqW54a5KkkT_3IUzJBYoBiCjdbF_5W_0N9AfNbcFs</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3103963506</pqid></control><display><type>article</type><title>Automated ASD detection in children from raw speech using customized STFT-CNN model</title><source>SpringerNature Journals</source><creator>Sai, Kurma Venkata Keerthana ; Krishna, Rompicharla Thanmayee ; Radha, Kodali ; Rao, Dhulipalla Venkata ; Muneera, Abdul</creator><creatorcontrib>Sai, Kurma Venkata Keerthana ; Krishna, Rompicharla Thanmayee ; Radha, Kodali ; Rao, Dhulipalla Venkata ; Muneera, Abdul</creatorcontrib><description>Autism spectrum disorder (ASD), a prevalent neurodevelopmental condition impacting cognitive, communicative, and behavioral aspects, typically manifests in early childhood due to genetic, environmental, and immunological factors. Employing a novel dataset termed children’s ASD speech corpus (CASD-SC), the research makes use of short-time Fourier transform (STFT) layered convolutional neural networks (CNN), incorporating an image input layer and a sequence input layer. The analysis encompasses data both with and without augmentation, exploring various CNN configurations. Results showcase that the log spectrogram-based STFT layered CNN model achieves 86.6% accuracy for the raw data, while the pre-emphasis filter (PEF) with learnables-based STFT layered CNN model attains 99.1% accuracy for the data with augmentation for detecting ASD in children. This investigation bridges the literature gap by evaluating child-specific raw speech data. The study underscores the significance of processing and training efficiency in ASD diagnosis and promotes early intervention techniques by improving ASD detection in children.</description><identifier>ISSN: 1381-2416</identifier><identifier>EISSN: 1572-8110</identifier><identifier>DOI: 10.1007/s10772-024-10131-7</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Artificial Intelligence ; Artificial neural networks ; Autism ; Children ; Data augmentation ; Engineering ; Fourier transforms ; Immunology ; Mass media ; Neural networks ; Signal,Image and Speech Processing ; Social Sciences ; Speech</subject><ispartof>International journal of speech technology, 2024, Vol.27 (3), p.701-716</ispartof><rights>The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. 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.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c1157-3b0f2e360e9620a27e00141cc30cb49ea04f105c122b717d0f478f78adfd2ad23</cites><orcidid>0000-0002-8064-0440</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s10772-024-10131-7$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s10772-024-10131-7$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Sai, Kurma Venkata Keerthana</creatorcontrib><creatorcontrib>Krishna, Rompicharla Thanmayee</creatorcontrib><creatorcontrib>Radha, Kodali</creatorcontrib><creatorcontrib>Rao, Dhulipalla Venkata</creatorcontrib><creatorcontrib>Muneera, Abdul</creatorcontrib><title>Automated ASD detection in children from raw speech using customized STFT-CNN model</title><title>International journal of speech technology</title><addtitle>Int J Speech Technol</addtitle><description>Autism spectrum disorder (ASD), a prevalent neurodevelopmental condition impacting cognitive, communicative, and behavioral aspects, typically manifests in early childhood due to genetic, environmental, and immunological factors. Employing a novel dataset termed children’s ASD speech corpus (CASD-SC), the research makes use of short-time Fourier transform (STFT) layered convolutional neural networks (CNN), incorporating an image input layer and a sequence input layer. The analysis encompasses data both with and without augmentation, exploring various CNN configurations. Results showcase that the log spectrogram-based STFT layered CNN model achieves 86.6% accuracy for the raw data, while the pre-emphasis filter (PEF) with learnables-based STFT layered CNN model attains 99.1% accuracy for the data with augmentation for detecting ASD in children. This investigation bridges the literature gap by evaluating child-specific raw speech data. The study underscores the significance of processing and training efficiency in ASD diagnosis and promotes early intervention techniques by improving ASD detection in children.</description><subject>Artificial Intelligence</subject><subject>Artificial neural networks</subject><subject>Autism</subject><subject>Children</subject><subject>Data augmentation</subject><subject>Engineering</subject><subject>Fourier transforms</subject><subject>Immunology</subject><subject>Mass media</subject><subject>Neural networks</subject><subject>Signal,Image and Speech Processing</subject><subject>Social Sciences</subject><subject>Speech</subject><issn>1381-2416</issn><issn>1572-8110</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE1PwzAMhiMEEmPwBzhF4hywk65pj9NggDSNw8Y5yvKxdVrbkbRC8OsJFIkbJ1vW-9jWQ8g1wi0CyLuIICVnwDOGgAKZPCEjnKRRgQinqRcFMp5hfk4uYtwDQClLPiKrad-1te6cpdPVPbWuc6ar2oZWDTW76mCDa6gPbU2Dfqfx6JzZ0T5WzZaaPia0-kzoaj1fs9lySevWusMlOfP6EN3Vbx2T1_nDevbEFi-Pz7PpghlMrzGxAc-dyMGVOQfNpQPADI0RYDZZ6TRkHmFikPONRGnBZ7LwstDWW64tF2NyM-w9hvatd7FT-7YPTTqpBIIoczGBPKX4kDKhjTE4r46hqnX4UAjqW54a5KkkT_3IUzJBYoBiCjdbF_5W_0N9AfNbcFs</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Sai, Kurma Venkata Keerthana</creator><creator>Krishna, Rompicharla Thanmayee</creator><creator>Radha, Kodali</creator><creator>Rao, Dhulipalla Venkata</creator><creator>Muneera, Abdul</creator><general>Springer US</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7T9</scope><orcidid>https://orcid.org/0000-0002-8064-0440</orcidid></search><sort><creationdate>2024</creationdate><title>Automated ASD detection in children from raw speech using customized STFT-CNN model</title><author>Sai, Kurma Venkata Keerthana ; Krishna, Rompicharla Thanmayee ; Radha, Kodali ; Rao, Dhulipalla Venkata ; Muneera, Abdul</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1157-3b0f2e360e9620a27e00141cc30cb49ea04f105c122b717d0f478f78adfd2ad23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial Intelligence</topic><topic>Artificial neural networks</topic><topic>Autism</topic><topic>Children</topic><topic>Data augmentation</topic><topic>Engineering</topic><topic>Fourier transforms</topic><topic>Immunology</topic><topic>Mass media</topic><topic>Neural networks</topic><topic>Signal,Image and Speech Processing</topic><topic>Social Sciences</topic><topic>Speech</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sai, Kurma Venkata Keerthana</creatorcontrib><creatorcontrib>Krishna, Rompicharla Thanmayee</creatorcontrib><creatorcontrib>Radha, Kodali</creatorcontrib><creatorcontrib>Rao, Dhulipalla Venkata</creatorcontrib><creatorcontrib>Muneera, Abdul</creatorcontrib><collection>CrossRef</collection><collection>Linguistics and Language Behavior Abstracts (LLBA)</collection><jtitle>International journal of speech technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Sai, Kurma Venkata Keerthana</au><au>Krishna, Rompicharla Thanmayee</au><au>Radha, Kodali</au><au>Rao, Dhulipalla Venkata</au><au>Muneera, Abdul</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated ASD detection in children from raw speech using customized STFT-CNN model</atitle><jtitle>International journal of speech technology</jtitle><stitle>Int J Speech Technol</stitle><date>2024</date><risdate>2024</risdate><volume>27</volume><issue>3</issue><spage>701</spage><epage>716</epage><pages>701-716</pages><issn>1381-2416</issn><eissn>1572-8110</eissn><abstract>Autism spectrum disorder (ASD), a prevalent neurodevelopmental condition impacting cognitive, communicative, and behavioral aspects, typically manifests in early childhood due to genetic, environmental, and immunological factors. Employing a novel dataset termed children’s ASD speech corpus (CASD-SC), the research makes use of short-time Fourier transform (STFT) layered convolutional neural networks (CNN), incorporating an image input layer and a sequence input layer. The analysis encompasses data both with and without augmentation, exploring various CNN configurations. Results showcase that the log spectrogram-based STFT layered CNN model achieves 86.6% accuracy for the raw data, while the pre-emphasis filter (PEF) with learnables-based STFT layered CNN model attains 99.1% accuracy for the data with augmentation for detecting ASD in children. This investigation bridges the literature gap by evaluating child-specific raw speech data. The study underscores the significance of processing and training efficiency in ASD diagnosis and promotes early intervention techniques by improving ASD detection in children.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s10772-024-10131-7</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0002-8064-0440</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1381-2416
ispartof International journal of speech technology, 2024, Vol.27 (3), p.701-716
issn 1381-2416
1572-8110
language eng
recordid cdi_proquest_journals_3103963506
source SpringerNature Journals
subjects Artificial Intelligence
Artificial neural networks
Autism
Children
Data augmentation
Engineering
Fourier transforms
Immunology
Mass media
Neural networks
Signal,Image and Speech Processing
Social Sciences
Speech
title Automated ASD detection in children from raw speech using customized STFT-CNN model
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T06%3A46%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automated%20ASD%20detection%20in%20children%20from%20raw%20speech%20using%20customized%20STFT-CNN%20model&rft.jtitle=International%20journal%20of%20speech%20technology&rft.au=Sai,%20Kurma%20Venkata%20Keerthana&rft.date=2024&rft.volume=27&rft.issue=3&rft.spage=701&rft.epage=716&rft.pages=701-716&rft.issn=1381-2416&rft.eissn=1572-8110&rft_id=info:doi/10.1007/s10772-024-10131-7&rft_dat=%3Cproquest_cross%3E3103963506%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3103963506&rft_id=info:pmid/&rfr_iscdi=true