{"id":"https://openalex.org/W2788381663","doi":"https://doi.org/10.1109/icassp.2018.8461802","title":"Sequence-Based Multi-Lingual Low Resource Speech Recognition","display_name":"Sequence-Based Multi-Lingual Low Resource Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2788381663","doi":"https://doi.org/10.1109/icassp.2018.8461802","mag":"2788381663"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.07420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"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":"Siddharth Dalmia","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053704856","display_name":"Ramon Sanabria","orcid":null},"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":"Ramon Sanabria","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]","institution_ids":["https://openalex.org/I74973139"]}]},{"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":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A.]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1827,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83821417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4909","last_page":"4913"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7852545380592346},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6471399664878845},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6072652339935303},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6048826575279236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.549588680267334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5464901924133301},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5168386101722717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5039026141166687},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5000357627868652},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49415281414985657},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.480092316865921},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2863329350948334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852545380592346},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6471399664878845},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6072652339935303},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6048826575279236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.549588680267334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5464901924133301},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5168386101722717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5039026141166687},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5000357627868652},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49415281414985657},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.480092316865921},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2863329350948334},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.07420","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.07420","pdf_url":"https://arxiv.org/pdf/1802.07420","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":"","raw_type":"text"},{"id":"mag:2788381663","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.07420.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.1802.07420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.07420","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":"pmh:oai:arXiv.org:1802.07420","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.07420","pdf_url":"https://arxiv.org/pdf/1802.07420","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6524269621","display_name":null,"funder_award_id":"OCI-1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6778350887","display_name":null,"funder_award_id":"1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7404166632","display_name":"Bridges: From Communities and Data to Workflows and Insight","funder_award_id":"1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8016956108","display_name":null,"funder_award_id":"HR0011-15-C-0114","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8293170275","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788381663.pdf","grobid_xml":"https://content.openalex.org/works/W2788381663.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W63916190","https://openalex.org/W1501286448","https://openalex.org/W1604771987","https://openalex.org/W1736701665","https://openalex.org/W1970890968","https://openalex.org/W1978660892","https://openalex.org/W1992912377","https://openalex.org/W1994606281","https://openalex.org/W2033436836","https://openalex.org/W2038810952","https://openalex.org/W2090764203","https://openalex.org/W2106440210","https://openalex.org/W2120209245","https://openalex.org/W2123798005","https://openalex.org/W2127141656","https://openalex.org/W2131042651","https://openalex.org/W2339821021","https://openalex.org/W2346660049","https://openalex.org/W2395416438","https://openalex.org/W2533523411","https://openalex.org/W2604132379","https://openalex.org/W2633221078","https://openalex.org/W2743818757","https://openalex.org/W2963211739","https://openalex.org/W6602656266","https://openalex.org/W6630162575","https://openalex.org/W6635896687","https://openalex.org/W6679446866"],"related_works":["https://openalex.org/W2963292011","https://openalex.org/W3102527112","https://openalex.org/W2971863715","https://openalex.org/W3155025376","https://openalex.org/W181192452","https://openalex.org/W3198429080","https://openalex.org/W3214299152","https://openalex.org/W3032300711","https://openalex.org/W2891816510","https://openalex.org/W2995813704","https://openalex.org/W2769437540","https://openalex.org/W2979120219","https://openalex.org/W3012172444","https://openalex.org/W2950961956","https://openalex.org/W2743818757","https://openalex.org/W3105242324","https://openalex.org/W3104842308","https://openalex.org/W2948552313","https://openalex.org/W2938099940","https://openalex.org/W3033831118"],"abstract_inverted_index":{"Techniques":[0],"for":[1,103,137,146],"multi-lingual":[2,45,55,147],"and":[3,16,22,36],"cross-lingual":[4,141],"speech":[5],"recognition":[6],"can":[7,113],"help":[8],"in":[9,26,87,99],"low":[10,139],"resource":[11,140],"scenarios,":[12,143],"to":[13,42,95,117,154],"bootstrap":[14],"systems":[15,97],"enable":[17],"analysis":[18],"of":[19,33,57,89,124],"new":[20],"languages":[21,82,134],"domains.":[23],"End-to-end":[24],"approaches,":[25],"particular":[27],"sequence-based":[28],"techniques,":[29],"are":[30],"attractive":[31],"because":[32],"their":[34],"simplicity":[35],"elegance.":[37],"While":[38],"it":[39,151],"is":[40,60,135],"possible":[41],"integrate":[43],"traditional":[44],"bottleneck":[46],"feature":[47],"extractors":[48],"as":[49],"front-ends,":[50],"we":[51],"show":[52,74,108,129],"that":[53,75,109,130],"end-to-end":[54],"training":[56,131],"sequence":[58],"models":[59,65],"effective":[61],"on":[62,80,132],"context":[63],"independent":[64],"trained":[66,111],"using":[67,121],"Connectionist":[68],"Temporal":[69],"Classification":[70],"(CTC)":[71],"loss.":[72],"We":[73,106,128],"our":[76],"model":[77,112],"improves":[78],"performance":[79],"Babel":[81],"by":[83],"over":[84],"6%":[85],"absolute":[86],"terms":[88],"word/phoneme":[90],"error":[91],"rate":[92],"when":[93],"compared":[94],"mono-lingual":[96],"built":[98],"the":[100,110,125],"same":[101],"setting":[102],"these":[104],"languages.":[105],"also":[107],"be":[114],"adapted":[115],"cross-lingually":[116],"an":[118],"unseen":[119],"language":[120],"just":[122],"25%":[123],"target":[126,142],"data.":[127],"multiple":[133],"important":[136],"very":[138],"but":[144],"not":[145],"testing":[148],"scenarios.":[149],"Here,":[150],"appears":[152],"beneficial":[153],"include":[155],"large":[156],"well":[157],"prepared":[158],"datasets.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}