{"id":"https://openalex.org/W2972581290","doi":"https://doi.org/10.21437/interspeech.2019-3052","title":"Multilingual Speech Recognition with Corpus Relatedness Sampling","display_name":"Multilingual Speech Recognition with Corpus Relatedness Sampling","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972581290","doi":"https://doi.org/10.21437/interspeech.2019-3052","mag":"2972581290"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3052","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"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":"Xinjian Li","raw_affiliation_strings":["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","https://openalex.org/I114772536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068873086","display_name":"Siddharth Dalmia","orcid":"https://orcid.org/0000-0003-0437-5988"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; U.S.A","institution_ids":["https://openalex.org/I74973139","https://openalex.org/I114772536"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; U.S.A","institution_ids":["https://openalex.org/I74973139","https://openalex.org/I114772536"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; U.S.A","institution_ids":["https://openalex.org/I74973139","https://openalex.org/I114772536"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2120","last_page":"2124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9990000128746033,"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":0.8638437986373901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6896898746490479},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6440025568008423},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6424210667610168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6120071411132812},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5633484125137329},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5211796164512634},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5100818276405334},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5096476078033447},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4737031161785126},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45808354020118713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4515681266784668},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4223720133304596},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.1888798475265503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8638437986373901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6896898746490479},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6440025568008423},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6424210667610168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6120071411132812},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5633484125137329},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5211796164512634},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5100818276405334},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5096476078033447},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4737031161785126},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45808354020118713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4515681266784668},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4223720133304596},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.1888798475265503},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-3052","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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"}],"funders":[{"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W1526236009","https://openalex.org/W1736701665","https://openalex.org/W1970890968","https://openalex.org/W1978660892","https://openalex.org/W2025198378","https://openalex.org/W2033436836","https://openalex.org/W2095629250","https://openalex.org/W2123798005","https://openalex.org/W2131042651","https://openalex.org/W2131744502","https://openalex.org/W2166637769","https://openalex.org/W2187089797","https://openalex.org/W2193413348","https://openalex.org/W2250357346","https://openalex.org/W2284628133","https://openalex.org/W2291975472","https://openalex.org/W2397721308","https://openalex.org/W2493916176","https://openalex.org/W2533523411","https://openalex.org/W2550821151","https://openalex.org/W2633221078","https://openalex.org/W2805993470","https://openalex.org/W2951559648","https://openalex.org/W2962893195","https://openalex.org/W2963292011","https://openalex.org/W2963390466","https://openalex.org/W2963946371"],"related_works":["https://openalex.org/W3096124370","https://openalex.org/W3150298331","https://openalex.org/W3031221932","https://openalex.org/W2150143935","https://openalex.org/W2574832780","https://openalex.org/W4388428244","https://openalex.org/W2791271059","https://openalex.org/W1975640689","https://openalex.org/W2203871458","https://openalex.org/W3138472290"],"abstract_inverted_index":{"Multilingual":[0],"acoustic":[1],"models":[2],"have":[3,13],"been":[4],"successfully":[5],"applied":[6],"to":[7,41,84,121],"low-resource":[8,153],"speech":[9],"recognition.Most":[10],"existing":[11],"works":[12],"combined":[14],"many":[15],"small":[16],"corpora":[17,48,125],"together,":[18],"and":[19,45,95,164],"pretrained":[20],"a":[21,61,68,71,78],"multilingual":[22,106,149],"model":[23,30,107,135,150],"by":[24],"sampling":[25,82,144],"from":[26,60,70,110,123],"each":[27,35,100,111,168],"corpus":[28,56,62,69,112,159],"uniformly.The":[29],"is":[31],"eventually":[32],"fine-tuned":[33,138],"on":[34,127,140,151],"target":[36,55,132,142],"corpus.This":[37],"approach,":[38],"however,":[39],"fails":[40],"exploit":[42],"the":[43,50,54,64,92,97,105,119,131,134,141,147,162],"relatedness":[44],"similarity":[46,98,129],"among":[47],"in":[49,63],"training":[51,104],"set.For":[52],"example,":[53],"might":[57],"benefit":[58],"more":[59],"same":[65],"domain":[66,165],"or":[67],"close":[72],"language.In":[73],"this":[74,88],"work,":[75],"we":[76,102,116,155],"propose":[77],"simple":[79],"but":[80],"useful":[81],"strategy":[83,145],"take":[85],"advantage":[86],"of":[87,167],"relatedness.We":[89],"first":[90],"compute":[91],"corpus-level":[93],"embeddings":[94,160],"estimate":[96],"between":[99],"corpus.Next":[101],"start":[103],"with":[108,130],"uniform-sampling":[109],"at":[113],"first,":[114],"then":[115],"gradually":[117],"increase":[118],"probability":[120],"sample":[122],"related":[124],"based":[126],"its":[128],"corpus.Finally":[133],"would":[136],"be":[137],"automatically":[139],"corpus.Our":[143],"outperforms":[146],"baseline":[148],"16":[152],"tasks.Additionally,":[154],"demonstrate":[156],"that":[157],"our":[158],"capture":[161],"language":[163],"information":[166],"corpus.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}