A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition
Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resou...
Gespeichert in:
| Veröffentlicht in: | IEICE Transactions on Information and Systems 2022/09/01, Vol.E105.D(9), pp.1639-1642 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1642 |
|---|---|
| container_issue | 9 |
| container_start_page | 1639 |
| container_title | IEICE Transactions on Information and Systems |
| container_volume | E105.D |
| creator | HUANG, Zheying XU, Ji ZHAO, Qingwei ZHANG, Pengyuan |
| description | Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method. |
| doi_str_mv | 10.1587/transinf.2022EDL8036 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2709089203</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2709089203</sourcerecordid><originalsourceid>FETCH-LOGICAL-c396t-4329c5c1ffaf4c3b93964b7147ba85546d607018de3dfbb0f363f9100e9ecbd03</originalsourceid><addsrcrecordid>eNpNUFtPwjAUbowmIvoPfFjic7Fdd-sj4aImMyaAvjZdd8qK0GI3Qvz3biLI0zk53-Xk-xC6p2RA4yx9bLy0tbF6EJIwnIzzjLDkAvVoGsWYsoReoh7hNMFZzMJrdFPXK0JoFtK4h7bDYLF3eOrWZTDyrq7xh1ybUjbG2WDhpbHGLoOplxvYO_8ZjNymMBbKYG-aKniFRuIcpP9laedbvAQ8b0FVdaf5FkBVwQyUW1rTmd6iKy3XNdz9zT56n04Wo2ecvz29jIY5VownDY5YyFWsqNZSR4oVvL1GRUqjtJBZHEdJmZC0DVECK3VREM0SpjklBDiooiSsjx4OvlvvvnZQN2Lldt62L0WYEk4yHhLWsqIDS3XZPWix9WYj_begRHTdimO34qzbVjY7yFZ1I5dwEknfGLWGf9GEkliMBT8uZyYnsqqkF2DZD2prjRM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2709089203</pqid></control><display><type>article</type><title>A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition</title><source>J-STAGE Free</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>HUANG, Zheying ; XU, Ji ; ZHAO, Qingwei ; ZHANG, Pengyuan</creator><creatorcontrib>HUANG, Zheying ; XU, Ji ; ZHAO, Qingwei ; ZHANG, Pengyuan</creatorcontrib><description>Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.</description><identifier>ISSN: 0916-8532</identifier><identifier>EISSN: 1745-1361</identifier><identifier>DOI: 10.1587/transinf.2022EDL8036</identifier><language>eng</language><publisher>Tokyo: The Institute of Electronics, Information and Communication Engineers</publisher><subject>code-switching ; Learning ; low-resource ; meta-learning ; Speech recognition ; Training ; two-fold cross-validation</subject><ispartof>IEICE Transactions on Information and Systems, 2022/09/01, Vol.E105.D(9), pp.1639-1642</ispartof><rights>2022 The Institute of Electronics, Information and Communication Engineers</rights><rights>Copyright Japan Science and Technology Agency 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c396t-4329c5c1ffaf4c3b93964b7147ba85546d607018de3dfbb0f363f9100e9ecbd03</citedby><cites>FETCH-LOGICAL-c396t-4329c5c1ffaf4c3b93964b7147ba85546d607018de3dfbb0f363f9100e9ecbd03</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,1876,27903,27904</link.rule.ids></links><search><creatorcontrib>HUANG, Zheying</creatorcontrib><creatorcontrib>XU, Ji</creatorcontrib><creatorcontrib>ZHAO, Qingwei</creatorcontrib><creatorcontrib>ZHANG, Pengyuan</creatorcontrib><title>A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition</title><title>IEICE Transactions on Information and Systems</title><addtitle>IEICE Trans. Inf. & Syst.</addtitle><description>Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.</description><subject>code-switching</subject><subject>Learning</subject><subject>low-resource</subject><subject>meta-learning</subject><subject>Speech recognition</subject><subject>Training</subject><subject>two-fold cross-validation</subject><issn>0916-8532</issn><issn>1745-1361</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNpNUFtPwjAUbowmIvoPfFjic7Fdd-sj4aImMyaAvjZdd8qK0GI3Qvz3biLI0zk53-Xk-xC6p2RA4yx9bLy0tbF6EJIwnIzzjLDkAvVoGsWYsoReoh7hNMFZzMJrdFPXK0JoFtK4h7bDYLF3eOrWZTDyrq7xh1ybUjbG2WDhpbHGLoOplxvYO_8ZjNymMBbKYG-aKniFRuIcpP9laedbvAQ8b0FVdaf5FkBVwQyUW1rTmd6iKy3XNdz9zT56n04Wo2ecvz29jIY5VownDY5YyFWsqNZSR4oVvL1GRUqjtJBZHEdJmZC0DVECK3VREM0SpjklBDiooiSsjx4OvlvvvnZQN2Lldt62L0WYEk4yHhLWsqIDS3XZPWix9WYj_begRHTdimO34qzbVjY7yFZ1I5dwEknfGLWGf9GEkliMBT8uZyYnsqqkF2DZD2prjRM</recordid><startdate>20220901</startdate><enddate>20220901</enddate><creator>HUANG, Zheying</creator><creator>XU, Ji</creator><creator>ZHAO, Qingwei</creator><creator>ZHANG, Pengyuan</creator><general>The Institute of Electronics, Information and Communication Engineers</general><general>Japan Science and Technology Agency</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20220901</creationdate><title>A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition</title><author>HUANG, Zheying ; XU, Ji ; ZHAO, Qingwei ; ZHANG, Pengyuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c396t-4329c5c1ffaf4c3b93964b7147ba85546d607018de3dfbb0f363f9100e9ecbd03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>code-switching</topic><topic>Learning</topic><topic>low-resource</topic><topic>meta-learning</topic><topic>Speech recognition</topic><topic>Training</topic><topic>two-fold cross-validation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>HUANG, Zheying</creatorcontrib><creatorcontrib>XU, Ji</creatorcontrib><creatorcontrib>ZHAO, Qingwei</creatorcontrib><creatorcontrib>ZHANG, Pengyuan</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEICE Transactions on Information and Systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>HUANG, Zheying</au><au>XU, Ji</au><au>ZHAO, Qingwei</au><au>ZHANG, Pengyuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition</atitle><jtitle>IEICE Transactions on Information and Systems</jtitle><addtitle>IEICE Trans. Inf. & Syst.</addtitle><date>2022-09-01</date><risdate>2022</risdate><volume>E105.D</volume><issue>9</issue><spage>1639</spage><epage>1642</epage><pages>1639-1642</pages><artnum>2022EDL8036</artnum><issn>0916-8532</issn><eissn>1745-1361</eissn><abstract>Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.</abstract><cop>Tokyo</cop><pub>The Institute of Electronics, Information and Communication Engineers</pub><doi>10.1587/transinf.2022EDL8036</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0916-8532 |
| ispartof | IEICE Transactions on Information and Systems, 2022/09/01, Vol.E105.D(9), pp.1639-1642 |
| issn | 0916-8532 1745-1361 |
| language | eng |
| recordid | cdi_proquest_journals_2709089203 |
| source | J-STAGE Free; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | code-switching Learning low-resource meta-learning Speech recognition Training two-fold cross-validation |
| title | A Two-Fold Cross-Validation Training Framework Combined with Meta-Learning for Code-Switching Speech Recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T10%3A36%3A54IST&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=A%20Two-Fold%20Cross-Validation%20Training%20Framework%20Combined%20with%20Meta-Learning%20for%20Code-Switching%20Speech%20Recognition&rft.jtitle=IEICE%20Transactions%20on%20Information%20and%20Systems&rft.au=HUANG,%20Zheying&rft.date=2022-09-01&rft.volume=E105.D&rft.issue=9&rft.spage=1639&rft.epage=1642&rft.pages=1639-1642&rft.artnum=2022EDL8036&rft.issn=0916-8532&rft.eissn=1745-1361&rft_id=info:doi/10.1587/transinf.2022EDL8036&rft_dat=%3Cproquest_cross%3E2709089203%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=2709089203&rft_id=info:pmid/&rfr_iscdi=true |