{"id":"https://openalex.org/W2099826692","doi":"https://doi.org/10.1109/icassp.2011.5947356","title":"An investigation of subspace modeling for phonetic and speaker variability in automatic speech recognition","display_name":"An investigation of subspace modeling for phonetic and speaker variability in automatic speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2099826692","doi":"https://doi.org/10.1109/icassp.2011.5947356","mag":"2099826692"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5077077136","display_name":"Richard C. Rose","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard Rose","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, Canada","[Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, Canada]","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103677827","display_name":"Shou-Chun Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shou-Chun Yin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, Montreal, Canada","[Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, Canada]","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033437280","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0002-3122-5881"},"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"]},{"id":"https://openalex.org/I4210107622","display_name":"Nuance Communications (Canada)","ror":"https://ror.org/01pshz178","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210107622","https://openalex.org/I4210125787"]}],"countries":["AT","CA"],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Nuance Communications, Inc., Montreal, Canada","Nuance Communications, Inc., Montr\u00e9al, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., Montreal, Canada","institution_ids":["https://openalex.org/I4210107622"]},{"raw_affiliation_string":"Nuance Communications, Inc., Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4508","last_page":"4511"},"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8788588047027588},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.8197216391563416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7958735227584839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.746254026889801},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7130644917488098},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5294627547264099},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.520347535610199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4744114577770233},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4650275707244873},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4375094771385193},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42799127101898193},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41913890838623047},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.41827547550201416},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41590791940689087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39953523874282837},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.20652514696121216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11771109700202942},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10224908590316772}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8788588047027588},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.8197216391563416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958735227584839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.746254026889801},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7130644917488098},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5294627547264099},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.520347535610199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4744114577770233},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4650275707244873},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4375094771385193},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42799127101898193},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41913890838623047},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.41827547550201416},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41590791940689087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39953523874282837},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.20652514696121216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11771109700202942},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10224908590316772},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.666.9057","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.666.9057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP+2011/pdfs/0004508.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310638","display_name":"McGill University","ror":"https://ror.org/01pxwe438"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W179430498","https://openalex.org/W222076935","https://openalex.org/W2069631319","https://openalex.org/W2096875330","https://openalex.org/W2123798005","https://openalex.org/W2136879537","https://openalex.org/W2151402979","https://openalex.org/W2165108269","https://openalex.org/W6607291291","https://openalex.org/W6608730375"],"related_works":["https://openalex.org/W2041695853","https://openalex.org/W1893339448","https://openalex.org/W1594739536","https://openalex.org/W2099826692","https://openalex.org/W2789430028","https://openalex.org/W2159208002","https://openalex.org/W2401394187","https://openalex.org/W2408222853","https://openalex.org/W1889546755","https://openalex.org/W2139140066"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,53,70,85,124,130],"impact":[4,83],"of":[5,32,66,84,92],"sub":[6],"space":[7],"based":[8,26,55,79,151],"techniques":[9],"for":[10,96,117],"acoustic":[11,46,80],"modeling":[12,47,88],"in":[13,48,73,87,112,129,146,154],"automatic":[14],"speech":[15,99],"recognition":[16,100],"(ASR).":[17],"There":[18],"are":[19],"many":[20],"well":[21],"known":[22],"approaches":[23],"to":[24,45,51,107,123,149],"subspace":[25,54,150],"speaker":[27,118,152,157],"adaptation":[28,158],"which":[29],"represent":[30],"sources":[31,91],"variability":[33,62,93],"as":[34,52,63],"a":[35,38,64,74,97,143],"projection":[36],"within":[37],"low":[39],"dimensional":[40],"subspace.":[41],"A":[42],"new":[43],"approach":[44],"ASR,":[49],"referred":[50],"Gaussian":[56],"mixture":[57],"model":[58,77],"(SGMM),":[59],"represents":[60,142],"phonetic":[61],"set":[65],"projections":[67],"applied":[68],"at":[69],"state":[71],"level":[72],"hidden":[75],"Markov":[76],"(HMM)":[78],"model.":[81],"The":[82,103,135],"SGMM":[86,104,140],"these":[89],"intrinsic":[90],"is":[94,105],"evaluated":[95],"continuous":[98,125],"(CSR)":[101],"task.":[102],"shown":[106],"provide":[108],"an":[109,155],"18%":[110],"reduction":[111,145],"word":[113],"error":[114],"rate":[115],"(WER)":[116],"independent":[119],"(SI)":[120],"ASR":[121],"relative":[122,148],"density":[126],"HMM":[127],"(CDHMM)":[128],"resource":[131],"management":[132],"CSR":[133],"domain.":[134],"SI":[136],"performance":[137],"obtained":[138],"from":[139],"also":[141],"5%":[144],"WER":[147],"adaption":[153],"unsupervised":[156],"scenario.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}