AM-MobileNet1D: A Portable Model for Speaker Recognition

Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks. The promising performance took these models to real-world ap...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-03
Hauptverfasser: João Antônio Chagas Nunes, Macêdo, David, Zanchettin, Cleber
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator João Antônio Chagas Nunes
Macêdo, David
Zanchettin, Cleber
description Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks. The promising performance took these models to real-world applications that becoming fundamentally end-user driven and mostly mobile. The mobile computation requires applications with reduced storage size, non-processing and memory intensive and efficient energy-consuming. The deep learning approaches, in contrast, usually are energy expensive, demanding storage, processing power, and memory. To address this demand, we propose a portable model called Additive Margin MobileNet1D (AM-MobileNet1D) to Speaker Identification on mobile devices. We evaluated the proposed approach on TIMIT and MIT datasets obtaining equivalent or better performances concerning the baseline methods. Additionally, the proposed model takes only 11.6 megabytes on disk storage against 91.2 from SincNet and AM-SincNet architectures, making the model seven times faster, with eight times fewer parameters.
doi_str_mv 10.48550/arxiv.2004.00132
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2004_00132</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2385542042</sourcerecordid><originalsourceid>FETCH-LOGICAL-a522-b05994a35d599eb49a9f04f45a5fe12cfee3b09e4a851b0d2316c85aede76e0a3</originalsourceid><addsrcrecordid>eNotkMtOwzAURC0kJKrSD2CFJdYJ19d2mrCLylNqAEH3kZ1co5QQBydF8PeEltVsjkZzhrEzAbFKtYZLE76brxgBVAwgJB6xGUopolQhnrDFMGwBAJMlai1nLM2LqPC2aemRRnF9xXP-7MNobEu88DW13PnAX3sy7xT4C1X-rWvGxnen7NiZdqDFf87Z5vZms7qP1k93D6t8HRmNGFnQWaaM1PWUZFVmMgfKKW20I4GVI5IWMlIm1cJCjVIkVaoN1bRMCIycs_ND7V6r7EPzYcJP-adX7vUm4uJA9MF_7mgYy63fhW7aVKKcHlEICuUvr8lQqw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2385542042</pqid></control><display><type>article</type><title>AM-MobileNet1D: A Portable Model for Speaker Recognition</title><source>arXiv.org</source><source>Free E- Journals</source><creator>João Antônio Chagas Nunes ; Macêdo, David ; Zanchettin, Cleber</creator><creatorcontrib>João Antônio Chagas Nunes ; Macêdo, David ; Zanchettin, Cleber</creatorcontrib><description>Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks. The promising performance took these models to real-world applications that becoming fundamentally end-user driven and mostly mobile. The mobile computation requires applications with reduced storage size, non-processing and memory intensive and efficient energy-consuming. The deep learning approaches, in contrast, usually are energy expensive, demanding storage, processing power, and memory. To address this demand, we propose a portable model called Additive Margin MobileNet1D (AM-MobileNet1D) to Speaker Identification on mobile devices. We evaluated the proposed approach on TIMIT and MIT datasets obtaining equivalent or better performances concerning the baseline methods. Additionally, the proposed model takes only 11.6 megabytes on disk storage against 91.2 from SincNet and AM-SincNet architectures, making the model seven times faster, with eight times fewer parameters.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2004.00132</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computation and Language ; Computer Science - Learning ; Computer Science - Sound ; Deep learning ; Electronic devices ; Energy storage ; Machine learning ; Mobile computing ; Speech recognition</subject><ispartof>arXiv.org, 2020-03</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/IJCNN48605.2020.9207519$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2004.00132$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>João Antônio Chagas Nunes</creatorcontrib><creatorcontrib>Macêdo, David</creatorcontrib><creatorcontrib>Zanchettin, Cleber</creatorcontrib><title>AM-MobileNet1D: A Portable Model for Speaker Recognition</title><title>arXiv.org</title><description>Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks. The promising performance took these models to real-world applications that becoming fundamentally end-user driven and mostly mobile. The mobile computation requires applications with reduced storage size, non-processing and memory intensive and efficient energy-consuming. The deep learning approaches, in contrast, usually are energy expensive, demanding storage, processing power, and memory. To address this demand, we propose a portable model called Additive Margin MobileNet1D (AM-MobileNet1D) to Speaker Identification on mobile devices. We evaluated the proposed approach on TIMIT and MIT datasets obtaining equivalent or better performances concerning the baseline methods. Additionally, the proposed model takes only 11.6 megabytes on disk storage against 91.2 from SincNet and AM-SincNet architectures, making the model seven times faster, with eight times fewer parameters.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Sound</subject><subject>Deep learning</subject><subject>Electronic devices</subject><subject>Energy storage</subject><subject>Machine learning</subject><subject>Mobile computing</subject><subject>Speech recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotkMtOwzAURC0kJKrSD2CFJdYJ19d2mrCLylNqAEH3kZ1co5QQBydF8PeEltVsjkZzhrEzAbFKtYZLE76brxgBVAwgJB6xGUopolQhnrDFMGwBAJMlai1nLM2LqPC2aemRRnF9xXP-7MNobEu88DW13PnAX3sy7xT4C1X-rWvGxnen7NiZdqDFf87Z5vZms7qP1k93D6t8HRmNGFnQWaaM1PWUZFVmMgfKKW20I4GVI5IWMlIm1cJCjVIkVaoN1bRMCIycs_ND7V6r7EPzYcJP-adX7vUm4uJA9MF_7mgYy63fhW7aVKKcHlEICuUvr8lQqw</recordid><startdate>20200331</startdate><enddate>20200331</enddate><creator>João Antônio Chagas Nunes</creator><creator>Macêdo, David</creator><creator>Zanchettin, Cleber</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200331</creationdate><title>AM-MobileNet1D: A Portable Model for Speaker Recognition</title><author>João Antônio Chagas Nunes ; Macêdo, David ; Zanchettin, Cleber</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a522-b05994a35d599eb49a9f04f45a5fe12cfee3b09e4a851b0d2316c85aede76e0a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Sound</topic><topic>Deep learning</topic><topic>Electronic devices</topic><topic>Energy storage</topic><topic>Machine learning</topic><topic>Mobile computing</topic><topic>Speech recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>João Antônio Chagas Nunes</creatorcontrib><creatorcontrib>Macêdo, David</creatorcontrib><creatorcontrib>Zanchettin, Cleber</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>João Antônio Chagas Nunes</au><au>Macêdo, David</au><au>Zanchettin, Cleber</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AM-MobileNet1D: A Portable Model for Speaker Recognition</atitle><jtitle>arXiv.org</jtitle><date>2020-03-31</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks. The promising performance took these models to real-world applications that becoming fundamentally end-user driven and mostly mobile. The mobile computation requires applications with reduced storage size, non-processing and memory intensive and efficient energy-consuming. The deep learning approaches, in contrast, usually are energy expensive, demanding storage, processing power, and memory. To address this demand, we propose a portable model called Additive Margin MobileNet1D (AM-MobileNet1D) to Speaker Identification on mobile devices. We evaluated the proposed approach on TIMIT and MIT datasets obtaining equivalent or better performances concerning the baseline methods. Additionally, the proposed model takes only 11.6 megabytes on disk storage against 91.2 from SincNet and AM-SincNet architectures, making the model seven times faster, with eight times fewer parameters.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2004.00132</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-03
issn 2331-8422
language eng
recordid cdi_arxiv_primary_2004_00132
source arXiv.org; Free E- Journals
subjects Computer Science - Computation and Language
Computer Science - Learning
Computer Science - Sound
Deep learning
Electronic devices
Energy storage
Machine learning
Mobile computing
Speech recognition
title AM-MobileNet1D: A Portable Model for Speaker Recognition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T18%3A56%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AM-MobileNet1D:%20A%20Portable%20Model%20for%20Speaker%20Recognition&rft.jtitle=arXiv.org&rft.au=Jo%C3%A3o%20Ant%C3%B4nio%20Chagas%20Nunes&rft.date=2020-03-31&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2004.00132&rft_dat=%3Cproquest_arxiv%3E2385542042%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2385542042&rft_id=info:pmid/&rfr_iscdi=true