{"id":"https://openalex.org/W9638664","doi":"https://doi.org/10.21437/interspeech.2007-271","title":"Handling OOV words in Arabic ASR via flexible morphological constraints","display_name":"Handling OOV words in Arabic ASR via flexible morphological constraints","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W9638664","doi":"https://doi.org/10.21437/interspeech.2007-271","mag":"9638664"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-271","doi":"https://doi.org/10.21437/interspeech.2007-271","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-271","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://publikationen.bibliothek.kit.edu/1000008825/359178","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081997186","display_name":"Nguy\u1ec5n B\u00e1ch","orcid":"https://orcid.org/0000-0002-9245-3298","observed_orcids":["https://orcid.org/0000-0002-9245-3298"]},"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":"Nguyen Bach","raw_affiliation_strings":["InterACT, Language Technologies Institute","School of Computer Science, Carnegie Mellon University Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031608369","display_name":"Mohamed Noamany","orcid":null,"observed_orcids":[]},"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":"Mohamed Noamany","raw_affiliation_strings":["InterACT, Language Technologies Institute","School of Computer Science, Carnegie Mellon University Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Richard Lane","orcid":null,"observed_orcids":[]},"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":"Ian Lane","raw_affiliation_strings":["InterACT, Language Technologies Institute","School of Computer Science, Carnegie Mellon University Pittsburgh, PA 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InterACT, Language Technologies Institute","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028","observed_orcids":["https://orcid.org/0000-0002-9809-7028"]},"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":"Tanja Schultz","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.2166,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.37887854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2373","last_page":"2376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.9739999771118164},{"id":"https://openalex.org/keywords/arabic-speech-recognition","display_name":"Arabic speech recognition","score":0.9800000190734863},{"id":"https://openalex.org/keywords/morphological-constraints","display_name":"morphological constraints","score":0.8629999756813049},{"id":"https://openalex.org/keywords/hybrid-language-models","display_name":"hybrid language models","score":0.6959999799728394},{"id":"https://openalex.org/keywords/subword-units","display_name":"subword units","score":0.953000009059906},{"id":"https://openalex.org/keywords/morphological-composition","display_name":"morphological composition","score":0.8199999928474426},{"id":"https://openalex.org/keywords/dictionary-lookup","display_name":"dictionary lookup","score":0.7689999938011169},{"id":"https://openalex.org/keywords/word-error-rate-reduction","display_name":"word error rate reduction","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237420916557312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7107396721839905},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.690409243106842},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6371785402297974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5895432829856873},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5506672859191895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5385367274284363},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.45228031277656555},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.42270708084106445},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10469970107078552},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08205357193946838},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06319960951805115},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2007-271","doi":"https://doi.org/10.21437/interspeech.2007-271","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-271","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000008825","doi":null,"is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000008825","pdf_url":"https://publikationen.bibliothek.kit.edu/1000008825/359178","source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.1356","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.1356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~tanja/Papers/BachSchultz_Interspeech2007.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:EVASTAR-Karlsruhe.de:1000008825","doi":null,"is_oa":true,"landing_page_url":"https://publikationen.bibliothek.kit.edu/1000008825","pdf_url":"https://publikationen.bibliothek.kit.edu/1000008825/359178","source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:conferenceObject"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W9638664.pdf","grobid_xml":"https://content.openalex.org/works/W9638664.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W39510643","https://openalex.org/W58893626","https://openalex.org/W1501139663","https://openalex.org/W1631260214","https://openalex.org/W1985952313","https://openalex.org/W2064203761","https://openalex.org/W2128014038","https://openalex.org/W2134756243","https://openalex.org/W2142222482","https://openalex.org/W2144523916","https://openalex.org/W2166850712","https://openalex.org/W2408350183","https://openalex.org/W4301749008"],"related_works":["https://openalex.org/W7096871038","https://openalex.org/W7060919141","https://openalex.org/W2166850712","https://openalex.org/W4301749008","https://openalex.org/W3135151149","https://openalex.org/W2400306577","https://openalex.org/W3161539047","https://openalex.org/W7098172375","https://openalex.org/W14331692","https://openalex.org/W2103744051"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,20],"novel":[3],"framework":[4,19],"to":[5,43],"detect":[6],"and":[7,26,52,62,72],"recognize":[8],"outof-vocabulary":[9],"(OOV)":[10],"words":[11,25,38],"in":[12],"automated":[13],"speech":[14],"recognition":[15,39,68],"(ASR).In":[16],"the":[17,74],"proposed":[18,55,75],"hybrid":[21],"language":[22],"model":[23],"combining":[24],"sub-word":[27],"units":[28],"is":[29],"incorporated":[30],"during":[31],"ASR":[32,65],"decoding":[33],"then":[34],"three":[35],"different":[36],"OOV":[37,45,81],"methods":[40],"are":[41],"applied":[42],"generate":[44],"word":[46],"hypotheses.Specifically,":[47],"dictionary":[48],"lookup,":[49],"morphological":[50],"composition,":[51],"direct":[53],"phoneme-to-grapheme.The":[54],"approach":[56,76],"successfully":[57],"reduced":[58],"WER":[59],"by":[60],"1.9%":[61],"1.6%":[63],"for":[64],"systems":[66],"with":[67],"vocabularies":[69],"of":[70,80],"30K":[71],"219K.Moreover,":[73],"correctly":[77],"recognized":[78],"5%":[79],"words.":[82]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}
