{"id":"https://openalex.org/W134006180","doi":"https://doi.org/10.21437/interspeech.2008-389","title":"Automatically learning speaker-independent acoustic subword units","display_name":"Automatically learning speaker-independent acoustic subword units","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W134006180","doi":"https://doi.org/10.21437/interspeech.2008-389","mag":"134006180"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-389","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/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 ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"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":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1333","last_page":"1336"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8170307874679565},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7927340269088745},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.7878161072731018},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.764458417892456},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7467412948608398},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.538631796836853},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5219011902809143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48873424530029297},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4551023542881012},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4455236494541168},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43225789070129395},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41110071539878845},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.404571533203125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36212751269340515},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32972362637519836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0796746015548706},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06911799311637878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170307874679565},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7927340269088745},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7878161072731018},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.764458417892456},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7467412948608398},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.538631796836853},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5219011902809143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48873424530029297},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4551023542881012},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4455236494541168},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43225789070129395},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41110071539878845},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.404571533203125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36212751269340515},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32972362637519836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0796746015548706},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06911799311637878},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.21437/interspeech.2008-389","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.167.4840","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.167.4840","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/interspeech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W31925794","https://openalex.org/W1508165687","https://openalex.org/W1651108041","https://openalex.org/W1918599710","https://openalex.org/W1950396994","https://openalex.org/W1971081490","https://openalex.org/W1988378063","https://openalex.org/W2002342963","https://openalex.org/W2101536075","https://openalex.org/W2117041980","https://openalex.org/W2162995740"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"We":[0,16],"investigate":[1],"methods":[2],"for":[3,57],"unsupervised":[4,118],"learning":[5],"of":[6,10,20,31,45,68,106],"sub-word":[7],"acoustic":[8],"units":[9,110],"a":[11,21,28,77,86],"language":[12],"directly":[13],"from":[14,60,85],"speech.":[15],"demonstrate":[17],"that":[18],"states":[19],"hidden":[22],"Markov":[23],"model":[24],"\u201cgrown":[25],"\u201d":[26],"using":[27],"novel":[29],"modification":[30],"the":[32,43,46,50,53,61,65,69,98,101,107],"maximum":[33],"likelihood":[34],"successive":[35],"state":[36,55],"splitting":[37],"algorithm":[38],"correspond":[39],"very":[40],"well":[41],"with":[42],"phones":[44,112],"language.":[47],"In":[48],"particular,":[49],"correspondence":[51,105],"between":[52,100],"Viterbi":[54],"sequence":[56],"unseen":[58],"speech":[59,70,84],"training":[62],"speaker":[63],"and":[64,74,103],"phone":[66],"transcription":[67],"is":[71],"over":[72],"85%,":[73],"generalizes":[75],"to":[76,83,93,111],"large":[78],"extent":[79],"(":[80,113],"\u223c":[81,114],"63%)":[82],"different":[87],"speaker.":[88],"Furthermore,":[89],"we":[90],"are":[91],"able":[92],"bridge":[94],"more":[95],"than":[96],"half":[97],"gap":[99],"speaker-dependent":[102],"cross-speaker":[104],"automatically":[108],"learned":[109],"75%":[115],"accuracy)":[116],"by":[117],"adaptation":[119],"via":[120],"MLLR.":[121],"1.":[122]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}