{"id":"https://openalex.org/W2111955662","doi":"https://doi.org/10.1109/taslp.2015.2496222","title":"Using Pronunciation-Based Morphological Subword Units to Improve OOV Handling in Keyword Search","display_name":"Using Pronunciation-Based Morphological Subword Units to Improve OOV Handling in Keyword Search","publication_year":2015,"publication_date":"2015-10-30","ids":{"openalex":"https://openalex.org/W2111955662","doi":"https://doi.org/10.1109/taslp.2015.2496222","mag":"2111955662"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2496222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2496222","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Google, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012115124","display_name":"Peter Baumann","orcid":"https://orcid.org/0000-0003-0991-6288"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Baumann","raw_affiliation_strings":["Department of Linguistics, Northwestern University, Evanston, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866618","display_name":"Hao Fang","orcid":"https://orcid.org/0000-0002-5015-6017"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Fang","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033912251","display_name":"Brian Hutchinson","orcid":"https://orcid.org/0000-0002-5537-008X"},"institutions":[{"id":"https://openalex.org/I52669646","display_name":"Western Washington University","ror":"https://ror.org/05wn7r715","country_code":"US","type":"education","lineage":["https://openalex.org/I52669646"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Hutchinson","raw_affiliation_strings":["Department of Computer Science, Western Washington University, Bellingham, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Western Washington University, Bellingham, WA, USA","institution_ids":["https://openalex.org/I52669646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082970015","display_name":"Aaron Jaech","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Jaech","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mari Ostendorf","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049920688","display_name":"Janet B. Pierrehumbert","orcid":"https://orcid.org/0000-0002-5989-3574"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Janet Pierrehumbert","raw_affiliation_strings":["Oxford e-Research Centre, University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oxford e-Research Centre, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1827,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90266113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"1","first_page":"79","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.9990000128746033,"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":0.8061116933822632},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8039836287498474},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.6393330693244934},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5651187300682068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5627979636192322},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.544657826423645},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5273876190185547},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5124519467353821},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4780169725418091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47662317752838135},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15523159503936768}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061116933822632},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8039836287498474},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.6393330693244934},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5651187300682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627979636192322},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.544657826423645},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5273876190185547},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5124519467353821},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4780169725418091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47662317752838135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15523159503936768},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2015.2496222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2496222","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:0dacae29-481f-4e96-8164-26d7f6e480f2","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:0dacae29-481f-4e96-8164-26d7f6e480f2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6038698723","display_name":null,"funder_award_id":"W911NF-12-C-0014","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W23025778","https://openalex.org/W32347851","https://openalex.org/W49437105","https://openalex.org/W58893626","https://openalex.org/W114193738","https://openalex.org/W183136171","https://openalex.org/W201532657","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1683106298","https://openalex.org/W1970064959","https://openalex.org/W2000654171","https://openalex.org/W2001331936","https://openalex.org/W2015688877","https://openalex.org/W2024991751","https://openalex.org/W2026369565","https://openalex.org/W2030694415","https://openalex.org/W2031804986","https://openalex.org/W2047205705","https://openalex.org/W2050469586","https://openalex.org/W2052274902","https://openalex.org/W2056346282","https://openalex.org/W2078349113","https://openalex.org/W2085628288","https://openalex.org/W2090736696","https://openalex.org/W2096257473","https://openalex.org/W2100397666","https://openalex.org/W2102625858","https://openalex.org/W2103589071","https://openalex.org/W2103635001","https://openalex.org/W2110625382","https://openalex.org/W2111338354","https://openalex.org/W2116930768","https://openalex.org/W2120284515","https://openalex.org/W2129059886","https://openalex.org/W2141315442","https://openalex.org/W2142937603","https://openalex.org/W2142986430","https://openalex.org/W2148986421","https://openalex.org/W2153141912","https://openalex.org/W2155921444","https://openalex.org/W2166221226","https://openalex.org/W2172083727","https://openalex.org/W2186490579","https://openalex.org/W2251711535","https://openalex.org/W2296590378","https://openalex.org/W2397766809","https://openalex.org/W2398829910","https://openalex.org/W2404324365","https://openalex.org/W2405940000","https://openalex.org/W2442329935","https://openalex.org/W2541478194","https://openalex.org/W2578686723","https://openalex.org/W2594610113","https://openalex.org/W6600906190","https://openalex.org/W6601343523","https://openalex.org/W6602415096","https://openalex.org/W6604666349","https://openalex.org/W6607418263","https://openalex.org/W6608128620","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6637516881","https://openalex.org/W6675502863","https://openalex.org/W6684572061","https://openalex.org/W6691575401","https://openalex.org/W6712476315","https://openalex.org/W6712947553","https://openalex.org/W6713450094","https://openalex.org/W6713667583","https://openalex.org/W6718561954","https://openalex.org/W6731979058"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W2080578089","https://openalex.org/W2179005426"],"abstract_inverted_index":{"Out-of-vocabulary":[0],"(OOV)":[1],"keywords":[2],"present":[3],"a":[4,24,117],"challenge":[5],"for":[6,127,131],"keyword":[7],"search":[8],"(KWS)":[9],"systems":[10],"especially":[11,130],"in":[12,53],"the":[13,101,105,110,114,123],"low-resource":[14,43],"setting.":[15],"Previous":[16],"research":[17],"has":[18],"centered":[19],"around":[20],"approaches":[21,40],"that":[22,47],"use":[23],"variety":[25],"of":[26,84,91],"subword":[27,38,50,65],"units":[28,51,66],"to":[29,74,82],"recover":[30],"OOV":[31,132],"words.":[32],"This":[33],"paper":[34],"systematically":[35],"investigates":[36],"morphology-based":[37],"modeling":[39],"on":[41],"seven":[42],"languages.":[44],"We":[45],"show":[46],"using":[48,100],"morphological":[49],"(morphs)":[52],"speech":[54],"recognition":[55],"decoding":[56],"is":[57,95,120],"substantially":[58],"better":[59,98],"than":[60,99],"expanding":[61],"word-decoded":[62],"lattices":[63],"into":[64],"including":[67],"phones,":[68],"syllables":[69],"and":[70,87],"morphs.":[71],"As":[72],"alternatives":[73],"grapheme-based":[75,102],"morphs,":[76,103],"we":[77],"apply":[78],"unsupervised":[79],"morphology":[80],"learning":[81],"sequences":[83],"phonemes,":[85],"graphones,":[86],"syllables.":[88],"Using":[89],"one":[90],"these":[92],"phone-based":[93],"morphs":[94],"almost":[96],"always":[97],"but":[104],"particular":[106],"choice":[107],"varies":[108],"with":[109],"language.":[111],"By":[112],"combining":[113],"different":[115],"methods,":[116],"substantial":[118],"gain":[119],"obtained":[121],"over":[122],"best":[124],"single":[125],"case":[126],"all":[128],"languages,":[129],"performance.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}