{"id":"https://openalex.org/W1989182512","doi":"https://doi.org/10.1109/slt.2014.7078612","title":"EM-based phoneme confusion matrix generation for low-resource spoken term detection","display_name":"EM-based phoneme confusion matrix generation for low-resource spoken term detection","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1989182512","doi":"https://doi.org/10.1109/slt.2014.7078612","mag":"1989182512"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/EM-based_Phoneme_Confusion_Matrix_Generation_for_Low-resource_Spoken_Term_Detection/6473342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101948386","display_name":"Di Xu","orcid":"https://orcid.org/0000-0003-3822-2189"},"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":"Di Xu","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, School of Computer Science Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377624","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0002-4749-2984"},"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":"Yun Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, School of Computer Science Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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/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, USA","Language Technologies Institute, School of Computer Science Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, School of Computer Science Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101948386"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.844,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80460827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"424","last_page":"429"},"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":0.9980000257492065,"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":0.9976999759674072,"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":0.8284382820129395},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7220098972320557},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6545038223266602},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.6220878958702087},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6179497241973877},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.6040707230567932},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5835577249526978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5251231789588928},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5234653353691101},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4676368236541748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43984484672546387},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3331564962863922},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10365837812423706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06304889917373657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8284382820129395},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7220098972320557},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6545038223266602},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.6220878958702087},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6179497241973877},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.6040707230567932},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5835577249526978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5251231789588928},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5234653353691101},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4676368236541748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43984484672546387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3331564962863922},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10365837812423706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06304889917373657},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"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/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},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt.2014.7078612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1063","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1063&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473342","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/EM-based_Phoneme_Confusion_Matrix_Generation_for_Low-resource_Spoken_Term_Detection/6473342","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473342.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473342.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473342","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/EM-based_Phoneme_Confusion_Matrix_Generation_for_Low-resource_Spoken_Term_Detection/6473342","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W56579646","https://openalex.org/W114193738","https://openalex.org/W247110447","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1847682101","https://openalex.org/W1848000237","https://openalex.org/W1925927243","https://openalex.org/W1981367467","https://openalex.org/W1985690171","https://openalex.org/W2001290563","https://openalex.org/W2004022680","https://openalex.org/W2017225228","https://openalex.org/W2021986193","https://openalex.org/W2022146129","https://openalex.org/W2049633694","https://openalex.org/W2087614022","https://openalex.org/W2090755665","https://openalex.org/W2105594594","https://openalex.org/W2142236754","https://openalex.org/W2594610113","https://openalex.org/W4298771022","https://openalex.org/W6602263706","https://openalex.org/W6604666349","https://openalex.org/W6609412284","https://openalex.org/W6638864335","https://openalex.org/W6639122881"],"related_works":["https://openalex.org/W2964976023","https://openalex.org/W1982477181","https://openalex.org/W2403083015","https://openalex.org/W4285488523","https://openalex.org/W2011367623","https://openalex.org/W4366202965","https://openalex.org/W1969293528","https://openalex.org/W2349679704","https://openalex.org/W4389633859","https://openalex.org/W2570625548"],"abstract_inverted_index":{"The":[0],"idea":[1],"of":[2,30,63,83,90],"using":[3],"a":[4,35,69],"data-driven":[5,39,75],"phoneme":[6],"confusion":[7],"matrix":[8],"(PCM)":[9],"to":[10,20],"enhance":[11],"speech":[12,22],"recognition":[13],"and":[14,48,67],"retrieval":[15],"performance":[16,82],"is":[17],"not":[18],"new":[19],"the":[21,37,60,81,84,88],"community.":[23],"Although":[24],"empirical":[25],"results":[26],"show":[27],"various":[28],"degrees":[29],"improvements":[31],"brought":[32],"by":[33],"introducing":[34],"PCM,":[36],"underlying":[38],"processes":[40],"introduced":[41],"in":[42],"most":[43],"papers":[44],"are":[45],"rather":[46],"ad-hoc":[47],"lack":[49],"rigorous":[50],"statistical":[51,61],"justifications.":[52],"In":[53],"this":[54],"paper":[55],"we":[56],"will":[57,79],"focus":[58,97],"on":[59,98],"aspects":[62],"PCM":[64,76],"generation,":[65],"propose":[66],"justify":[68],"novel":[70],"expectation-maximization":[71],"based":[72],"algorithm":[73],"for":[74],"generation.":[77],"We":[78],"evaluate":[80],"generated":[85],"PCMs":[86],"under":[87],"context":[89],"low-resource":[91],"spoken":[92],"term":[93],"detection,":[94],"with":[95],"primary":[96],"out-of-vocabulary":[99],"keywords.":[100]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
