{"id":"https://openalex.org/W2948845926","doi":"https://doi.org/10.18653/v1/p19-1179","title":"Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation","display_name":"Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2948845926","doi":"https://doi.org/10.18653/v1/p19-1179","mag":"2948845926"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1179","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1179","pdf_url":"https://www.aclweb.org/anthology/P19-1179.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1179.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028564314","display_name":"Elizabeth Salesky","orcid":"https://orcid.org/0000-0001-6765-1447"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Elizabeth Salesky","raw_affiliation_strings":["Carnegie Mellon University, USA","Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024736091","display_name":"Matthias Sperber","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Sperber","raw_affiliation_strings":["Karlsruhe Institute of Technology, Germany","Karlsruhe Institute of Technology, Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W Black","raw_affiliation_strings":["Carnegie Mellon University, USA","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028564314"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.76808873,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77555389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1835","last_page":"1841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7812799215316772},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7124592661857605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6704940795898438},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6082825660705566},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5867899656295776},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5772782564163208},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5393756031990051},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4826505780220032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4360945224761963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7812799215316772},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7124592661857605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6704940795898438},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6082825660705566},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5867899656295776},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5772782564163208},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5393756031990051},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4826505780220032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4360945224761963},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p19-1179","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1179","pdf_url":"https://www.aclweb.org/anthology/P19-1179.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.01199","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01199","pdf_url":"https://arxiv.org/pdf/1906.01199","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2948845926","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.01199.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.01199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.01199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1179","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1179","pdf_url":"https://www.aclweb.org/anthology/P19-1179.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948845926.pdf","grobid_xml":"https://content.openalex.org/works/W2948845926.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2116648050","https://openalex.org/W2183341477","https://openalex.org/W2295297373","https://openalex.org/W2327501763","https://openalex.org/W2507959295","https://openalex.org/W2530876040","https://openalex.org/W2563850823","https://openalex.org/W2593011301","https://openalex.org/W2762715843","https://openalex.org/W2788575190","https://openalex.org/W2792296443","https://openalex.org/W2794753807","https://openalex.org/W2794999731","https://openalex.org/W2795138957","https://openalex.org/W2888958984","https://openalex.org/W2891066653","https://openalex.org/W2897414631","https://openalex.org/W2950613790","https://openalex.org/W2962784628","https://openalex.org/W2963086938","https://openalex.org/W2963266340","https://openalex.org/W2963946371","https://openalex.org/W2964121744","https://openalex.org/W3012492057"],"related_works":["https://openalex.org/W2981978471","https://openalex.org/W2899134946","https://openalex.org/W2354692305","https://openalex.org/W2101918136","https://openalex.org/W1794229635","https://openalex.org/W3112480982","https://openalex.org/W1969844544","https://openalex.org/W2047349592","https://openalex.org/W2964273755","https://openalex.org/W2068176618","https://openalex.org/W2971046054","https://openalex.org/W2914051086","https://openalex.org/W2030654686","https://openalex.org/W2397798422","https://openalex.org/W2766557690","https://openalex.org/W3015774380","https://openalex.org/W2884483159","https://openalex.org/W3196659080","https://openalex.org/W3015648588","https://openalex.org/W2899377381"],"abstract_inverted_index":{"Previous":[0],"work":[1],"on":[2,79],"end-to-end":[3],"translation":[4,41],"from":[5],"speech":[6,13,32,45,53],"has":[7],"primarily":[8],"used":[9],"frame-level":[10,44],"features":[11],"as":[12],"representations,":[14],"which":[15],"creates":[16],"longer,":[17],"sparser":[18],"sequences":[19,68],"than":[20,42],"text.":[21],"We":[22,71],"show":[23],"that":[24],"a":[25,89],"naive":[26],"method":[27],"to":[28,63,76],"create":[29,64],"compressed":[30],"phoneme-like":[31],"representations":[33],"is":[34],"far":[35],"more":[36],"effective":[37],"and":[38,55,83,103],"efficient":[39],"for":[40,52,69],"traditional":[43],"features.":[46],"Specifically,":[47],"we":[48],"generate":[49],"phoneme":[50],"labels":[51],"frames":[54,58],"average":[56],"consecutive":[57],"with":[59,88],"the":[60],"same":[61],"label":[62],"shorter,":[65],"higher-level":[66],"source":[67],"translation.":[70],"see":[72],"improvements":[73,97],"of":[74,94],"up":[75],"5":[77],"BLEU":[78],"both":[80],"our":[81],"high":[82],"low":[84],"resource":[85],"language":[86,105],"pairs,":[87],"reduction":[90],"in":[91],"training":[92],"time":[93],"60%.":[95],"Our":[96],"hold":[98],"across":[99],"multiple":[100],"data":[101],"sizes":[102],"two":[104],"pairs.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}