{"id":"https://openalex.org/W214260248","doi":"https://doi.org/10.21437/interspeech.2010-17","title":"Incorporating sparse representation phone identification features in automatic speech recognition using exponential families","display_name":"Incorporating sparse representation phone identification features in automatic speech recognition using exponential families","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W214260248","doi":"https://doi.org/10.21437/interspeech.2010-17","mag":"214260248"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5034451965","display_name":"Vaibhava Goel","orcid":"https://orcid.org/0000-0002-5504-3863"},"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":"Vaibhava Goel","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"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":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037212510","display_name":"Peder A. Olsen","orcid":"https://orcid.org/0000-0002-3836-8017"},"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":"Peder Olsen","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007586881","display_name":"D. Nahamoo","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"David Nahamoo","raw_affiliation_strings":["Nuance Communications (Austria), Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications (Austria), Vienna, Austria","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046671967","display_name":"Dimitri Kanevsky","orcid":null},"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":"Dimitri Kanevsky","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1345","last_page":"1348"},"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":0.9998000264167786,"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":0.7536724209785461},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7386900186538696},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6782805323600769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6638487577438354},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6284474730491638},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.572334885597229},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5476580262184143},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5354295969009399},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5263862609863281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5017993450164795},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47255513072013855},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4595254063606262},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.45511913299560547},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4387863874435425},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.43769463896751404},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42496025562286377},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17053428292274475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536724209785461},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7386900186538696},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6782805323600769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6638487577438354},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6284474730491638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.572334885597229},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5476580262184143},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5354295969009399},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5263862609863281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5017993450164795},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47255513072013855},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4595254063606262},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45511913299560547},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4387863874435425},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.43769463896751404},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42496025562286377},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17053428292274475},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W29339672","https://openalex.org/W256962426","https://openalex.org/W1904457459","https://openalex.org/W1966032357","https://openalex.org/W2097978681","https://openalex.org/W2114016253","https://openalex.org/W2125234026","https://openalex.org/W2156983866","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2153098279","https://openalex.org/W2061937230","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2189081180"],"abstract_inverted_index":{"Sparse":[0],"representation":[1],"phone":[2,16,32],"identification":[3],"features":[4,49,90],"(SPIF)":[5],"is":[6,106],"a":[7,66,93],"recently":[8],"developed":[9],"technique":[10],"to":[11,65,88,103,108,121],"obtain":[12],"an":[13,21],"estimate":[14],"of":[15,50,68,73,98],"posterior":[17,33],"probabilities":[18],"conditioned":[19],"on":[20],"acoustic":[22],"feature":[23,75],"vector.":[24],"In":[25],"this":[26,105],"paper,":[27],"we":[28],"explore":[29],"incorporating":[30],"SPIF":[31],"probability":[34],"estimates":[35],"in":[36,92],"large":[37],"vocabulary":[38],"continuous":[39],"speech":[40],"recognition":[41],"(LVCSR)":[42],"task":[43],"by":[44],"including":[45],"them":[46],"as":[47],"additional":[48],"exponential":[51,86],"densities":[52],"that":[53,84],"model":[54],"the":[55,127],"HMM":[56],"state":[57],"emission":[58],"likelihoods.":[59],"We":[60],"compare":[61],"our":[62],"proposed":[63],"approach":[64],"number":[67],"other":[69],"well":[70],"known":[71],"methods":[72],"combining":[74],"streams":[76],"or":[77,125],"multiple":[78,123],"LVCSR":[79],"systems.":[80],"Our":[81],"experiments":[82],"show":[83],"using":[85],"models":[87],"combine":[89],"results":[91],"word":[94],"error":[95,110],"rate":[96,111],"reduction":[97,112],"0.5%":[99],"absolute":[100],"(18.7%":[101],"down":[102],"18.2%);":[104],"comparable":[107],"best":[109],"obtained":[113],"from":[114],"system":[115,128],"combination":[116,129],"methods,":[117],"but":[118],"without":[119],"having":[120],"build":[122],"systems":[124],"tune":[126],"weights.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}