Massively Multilingual Adversarial Speech Recognition
We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the dimensions of phonetics, phonology, language family, geographical...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Adams, Oliver Wiesner, Matthew Watanabe, Shinji Yarowsky, David |
| description | We report on adaptation of multilingual end-to-end speech recognition models
trained on as many as 100 languages. Our findings shed light on the relative
importance of similarity between the target and pretraining languages along the
dimensions of phonetics, phonology, language family, geographical location, and
orthography. In this context, experiments demonstrate the effectiveness of two
additional pretraining objectives in encouraging language-independent encoder
representations: a context-independent phoneme objective paired with a
language-adversarial classification objective. |
| doi_str_mv | 10.48550/arxiv.1904.02210 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1904_02210</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1904_02210</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-fc48fa152012f30f9b0bc5fd47555aab0aa1b2f535174e2772438a2b837fe8ba3</originalsourceid><addsrcrecordid>eNotzstuwjAQhWFvukC0D8CqeYGE8WWwWSJUChIIiWYfjYMNltyAHIjg7bmuzr86-hgbcCiUQYQhpUvoCj4GVYAQHHoMV9S2oXPxmq3O8RRiaHZnitlk27nUUgr3_js6V--zjasPuyacwqH5ZB-eYuu-3ttn5eynnM7z5fp3MZ0scxppyH2tjCeOArjwEvzYgq3Rb5VGRCILRNwKjxK5Vk5oLZQ0JKyR2jtjSfbZ9-v26a6OKfxTulYPf_X0yxsGREAz</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Massively Multilingual Adversarial Speech Recognition</title><source>arXiv.org</source><creator>Adams, Oliver ; Wiesner, Matthew ; Watanabe, Shinji ; Yarowsky, David</creator><creatorcontrib>Adams, Oliver ; Wiesner, Matthew ; Watanabe, Shinji ; Yarowsky, David</creatorcontrib><description>We report on adaptation of multilingual end-to-end speech recognition models
trained on as many as 100 languages. Our findings shed light on the relative
importance of similarity between the target and pretraining languages along the
dimensions of phonetics, phonology, language family, geographical location, and
orthography. In this context, experiments demonstrate the effectiveness of two
additional pretraining objectives in encouraging language-independent encoder
representations: a context-independent phoneme objective paired with a
language-adversarial classification objective.</description><identifier>DOI: 10.48550/arxiv.1904.02210</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Learning</subject><creationdate>2019-04</creationdate><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1904.02210$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1904.02210$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Adams, Oliver</creatorcontrib><creatorcontrib>Wiesner, Matthew</creatorcontrib><creatorcontrib>Watanabe, Shinji</creatorcontrib><creatorcontrib>Yarowsky, David</creatorcontrib><title>Massively Multilingual Adversarial Speech Recognition</title><description>We report on adaptation of multilingual end-to-end speech recognition models
trained on as many as 100 languages. Our findings shed light on the relative
importance of similarity between the target and pretraining languages along the
dimensions of phonetics, phonology, language family, geographical location, and
orthography. In this context, experiments demonstrate the effectiveness of two
additional pretraining objectives in encouraging language-independent encoder
representations: a context-independent phoneme objective paired with a
language-adversarial classification objective.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzstuwjAQhWFvukC0D8CqeYGE8WWwWSJUChIIiWYfjYMNltyAHIjg7bmuzr86-hgbcCiUQYQhpUvoCj4GVYAQHHoMV9S2oXPxmq3O8RRiaHZnitlk27nUUgr3_js6V--zjasPuyacwqH5ZB-eYuu-3ttn5eynnM7z5fp3MZ0scxppyH2tjCeOArjwEvzYgq3Rb5VGRCILRNwKjxK5Vk5oLZQ0JKyR2jtjSfbZ9-v26a6OKfxTulYPf_X0yxsGREAz</recordid><startdate>20190403</startdate><enddate>20190403</enddate><creator>Adams, Oliver</creator><creator>Wiesner, Matthew</creator><creator>Watanabe, Shinji</creator><creator>Yarowsky, David</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190403</creationdate><title>Massively Multilingual Adversarial Speech Recognition</title><author>Adams, Oliver ; Wiesner, Matthew ; Watanabe, Shinji ; Yarowsky, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-fc48fa152012f30f9b0bc5fd47555aab0aa1b2f535174e2772438a2b837fe8ba3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Adams, Oliver</creatorcontrib><creatorcontrib>Wiesner, Matthew</creatorcontrib><creatorcontrib>Watanabe, Shinji</creatorcontrib><creatorcontrib>Yarowsky, David</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Adams, Oliver</au><au>Wiesner, Matthew</au><au>Watanabe, Shinji</au><au>Yarowsky, David</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Massively Multilingual Adversarial Speech Recognition</atitle><date>2019-04-03</date><risdate>2019</risdate><abstract>We report on adaptation of multilingual end-to-end speech recognition models
trained on as many as 100 languages. Our findings shed light on the relative
importance of similarity between the target and pretraining languages along the
dimensions of phonetics, phonology, language family, geographical location, and
orthography. In this context, experiments demonstrate the effectiveness of two
additional pretraining objectives in encouraging language-independent encoder
representations: a context-independent phoneme objective paired with a
language-adversarial classification objective.</abstract><doi>10.48550/arxiv.1904.02210</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1904.02210 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1904_02210 |
| source | arXiv.org |
| subjects | Computer Science - Computation and Language Computer Science - Learning |
| title | Massively Multilingual Adversarial Speech Recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T05%3A15%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Massively%20Multilingual%20Adversarial%20Speech%20Recognition&rft.au=Adams,%20Oliver&rft.date=2019-04-03&rft_id=info:doi/10.48550/arxiv.1904.02210&rft_dat=%3Carxiv_GOX%3E1904_02210%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |