{"id":"https://openalex.org/W2161347627","doi":"https://doi.org/10.1109/icassp.2008.4518671","title":"Universal background model based speech recognition","display_name":"Universal background model based speech recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2161347627","doi":"https://doi.org/10.1109/icassp.2008.4518671","mag":"2161347627"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518671","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113805086","display_name":"Stephen M. Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen M. Chu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114118962","display_name":"Balakrishnan Varadarajan","orcid":null},"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":"Balakrishnan Varadarajan","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"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":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4561","last_page":"4564"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6643087267875671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6069886088371277},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6021527647972107},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5115123987197876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5049214959144592},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4888615012168884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4439455270767212},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.42819932103157043},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32786834239959717},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10373836755752563},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0964098572731018},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06326332688331604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643087267875671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6069886088371277},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6021527647972107},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5115123987197876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5049214959144592},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4888615012168884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4439455270767212},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.42819932103157043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32786834239959717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10373836755752563},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0964098572731018},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06326332688331604},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2008.4518671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518671","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.167.4580","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.167.4580","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/people/balakris/pubs/icassp08_ubm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W72757270","https://openalex.org/W1542753413","https://openalex.org/W1934041838","https://openalex.org/W2041823554","https://openalex.org/W2106554350","https://openalex.org/W2111977926","https://openalex.org/W2167133962","https://openalex.org/W2408469387"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W3125766170","https://openalex.org/W2040641410"],"abstract_inverted_index":{"The":[0,71],"<i":[1,4,7],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[2,5,8],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">universal</i>":[3],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">background</i>":[6],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">model</i>":[9],"(UBM)":[10],"is":[11,75],"an":[12],"effective":[13],"framework":[14],"widely":[15],"used":[16],"in":[17,48,93],"speaker":[18],"recognition.":[19],"But":[20],"so":[21],"far":[22],"it":[23],"has":[24],"received":[25],"little":[26],"attention":[27],"from":[28],"the":[29,43],"speech":[30,82],"recognition":[31,83],"field.":[32],"In":[33],"this":[34,94],"work,":[35],"we":[36],"make":[37],"a":[38,52,61,78,86],"first":[39],"attempt":[40],"to":[41,45,68],"apply":[42],"UBM":[44,73],"acoustic":[46],"modeling":[47],"ASR.":[49],"We":[50],"propose":[51],"tree-based":[53],"parameter":[54],"estimation":[55],"technique":[56],"for":[57],"UBMs,":[58],"and":[59,65],"describe":[60],"set":[62],"of":[63],"smoothing":[64],"pruning":[66],"methods":[67],"facilitate":[69],"learning.":[70],"proposed":[72],"approach":[74],"benchmarked":[76],"on":[77,85],"state-of-the-art":[79],"large-vocabulary":[80],"continuous":[81],"platform":[84],"broadcast":[87],"transcription":[88],"task.":[89],"Preliminary":[90],"experiments":[91],"reported":[92],"paper":[95],"already":[96],"show":[97],"very":[98],"exciting":[99],"results.":[100]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":7},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
