{"id":"https://openalex.org/W1993660824","doi":"https://doi.org/10.1109/icassp.2013.6638959","title":"Deep neural network features and semi-supervised training for low resource speech recognition","display_name":"Deep neural network features and semi-supervised training for low resource speech recognition","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1993660824","doi":"https://doi.org/10.1109/icassp.2013.6638959","mag":"1993660824"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-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/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA","Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Microsoft Research, Redmond, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016543371","display_name":"Kenneth Church","orcid":"https://orcid.org/0000-0001-8378-6069"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Church","raw_affiliation_strings":["IBM Research, USA","IBM Research, Yorktown Heights,, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]},{"raw_affiliation_string":"IBM Research, Yorktown Heights,, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA","Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":21.7466,"has_fulltext":false,"cited_by_count":137,"citation_normalized_percentile":{"value":0.99412969,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6704","last_page":"6708"},"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/T10860","display_name":"Speech 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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8277931809425354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6902632713317871},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.667290985584259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6144534349441528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6003084778785706},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5845034718513489},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5786746740341187},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5598804354667664},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5184371471405029},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5139374136924744},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47001293301582336},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4613533020019531},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.43900150060653687},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4359695315361023},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3906722068786621},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36739063262939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277931809425354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6902632713317871},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.667290985584259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6144534349441528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003084778785706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5845034718513489},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5786746740341187},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5598804354667664},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5184371471405029},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5139374136924744},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47001293301582336},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4613533020019531},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.43900150060653687},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4359695315361023},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3906722068786621},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36739063262939453},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2013.6638959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.8071","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.8071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/~samuel/pdfs/dnn_semisup_lr.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.645.759","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.645.759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hltcoe.jhu.edu/uploads/publications/papers/16656_slides.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W55333121","https://openalex.org/W139772320","https://openalex.org/W165878654","https://openalex.org/W169882265","https://openalex.org/W217970951","https://openalex.org/W1526995323","https://openalex.org/W1534441687","https://openalex.org/W1555037511","https://openalex.org/W1991180839","https://openalex.org/W2012897754","https://openalex.org/W2076794394","https://openalex.org/W2090861223","https://openalex.org/W2105099419","https://openalex.org/W2110073835","https://openalex.org/W2110798204","https://openalex.org/W2120137673","https://openalex.org/W2123237149","https://openalex.org/W2123798005","https://openalex.org/W2126315862","https://openalex.org/W2127982613","https://openalex.org/W2130414229","https://openalex.org/W2131042651","https://openalex.org/W2136922672","https://openalex.org/W2138857742","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2170580867","https://openalex.org/W2184045248","https://openalex.org/W2399153411","https://openalex.org/W2403234505","https://openalex.org/W2407441242","https://openalex.org/W2407897255","https://openalex.org/W2606321545","https://openalex.org/W3148201686","https://openalex.org/W6605668731","https://openalex.org/W6606723699","https://openalex.org/W6606983177","https://openalex.org/W6608710415","https://openalex.org/W6631419337","https://openalex.org/W6631781866","https://openalex.org/W6676481782","https://openalex.org/W6678292227","https://openalex.org/W6680300913","https://openalex.org/W6712585555","https://openalex.org/W6713135925","https://openalex.org/W6714284179","https://openalex.org/W6890491316"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W3104108945","https://openalex.org/W2033364610","https://openalex.org/W3163689946","https://openalex.org/W2797776314","https://openalex.org/W2153927146","https://openalex.org/W2091066410"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,67],"new":[3],"technique":[4],"for":[5,15,34],"training":[6,32,47,77],"deep":[7],"neural":[8],"networks":[9],"(DNNs)":[10],"as":[11],"data-driven":[12],"feature":[13,52],"front-ends":[14],"large":[16],"vocabulary":[17],"continuous":[18],"speech":[19],"recognition":[20],"(LVCSR)":[21],"in":[22,37,66],"low":[23],"resource":[24],"settings.":[25],"To":[26],"circumvent":[27],"the":[28,50,57,90],"lack":[29],"of":[30,64,75,83],"sufficient":[31],"data":[33,44],"acoustic":[35],"modeling":[36],"these":[38,84],"scenarios,":[39],"we":[40],"use":[41],"transcribed":[42],"multilingual":[43],"and":[45],"semi-supervised":[46,94],"to":[48,81],"build":[49],"proposed":[51,58],"front-ends.":[53],"In":[54],"our":[55],"experiments,":[56],"features":[59],"provide":[60],"an":[61],"absolute":[62],"improvement":[63],"16%":[65],"low-resource":[68],"LVCSR":[69],"setting":[70],"with":[71],"only":[72],"one":[73],"hour":[74],"in-domain":[76],"data.":[78],"While":[79],"close":[80],"three-fourths":[82],"gains":[85],"come":[86],"from":[87,93],"DNN-based":[88],"features,":[89],"remaining":[91],"are":[92],"training.":[95]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":5}],"updated_date":"2026-04-05T06:14:27.290980","created_date":"2025-10-10T00:00:00"}