{"id":"https://openalex.org/W1981185131","doi":"https://doi.org/10.1109/iscslp.2014.6936584","title":"Speaker adaptive bottleneck features extraction for LVCSR based on discriminative learning of speaker codes","display_name":"Speaker adaptive bottleneck features extraction for LVCSR based on discriminative learning of speaker codes","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W1981185131","doi":"https://doi.org/10.1109/iscslp.2014.6936584","mag":"1981185131"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language 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/A5042701682","display_name":"Changqing Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changqing Kong","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083184776","display_name":"Shaofei Xue","orcid":"https://orcid.org/0000-0001-6199-7965"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Xue","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020540834","display_name":"Jianqing Gao","orcid":"https://orcid.org/0000-0001-5575-4940"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqing Gao","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","iFlytek Research, Anhui USTC iFlytek Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFlytek Research, Anhui USTC iFlytek Co., Ltd., China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210133256","display_name":"Instituttet for Anvendt Datateknik (Denmark)","ror":"https://ror.org/02q83se13","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210133256"]}],"countries":["CN","DK"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["Iflytek Research, Anhui USTC iFlytek Co., Ltd","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iflytek Research, Anhui USTC iFlytek Co., Ltd","institution_ids":["https://openalex.org/I4210133256"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, York University","[Department of Electrical Engineering & Computer Science, York University, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, York University","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"[Department of Electrical Engineering & Computer Science, York University, Canada]","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"83","last_page":"87"},"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":0.9962000250816345,"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":0.992900013923645,"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":0.8074353933334351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7918105125427246},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7782971858978271},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7098454236984253},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6713439226150513},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6659534573554993},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6487895250320435},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5124390721321106},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.510246992111206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4617946147918701},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4401406943798065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43894654512405396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41846203804016113},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06265383958816528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074353933334351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7918105125427246},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7782971858978271},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7098454236984253},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6713439226150513},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6659534573554993},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6487895250320435},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5124390721321106},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.510246992111206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4617946147918701},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4401406943798065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43894654512405396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41846203804016113},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06265383958816528},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W11553578","https://openalex.org/W1513862252","https://openalex.org/W1975138161","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2012897754","https://openalex.org/W2016084804","https://openalex.org/W2036351241","https://openalex.org/W2039671743","https://openalex.org/W2046899276","https://openalex.org/W2052248915","https://openalex.org/W2063689849","https://openalex.org/W2080005694","https://openalex.org/W2090320273","https://openalex.org/W2100495367","https://openalex.org/W2100969003","https://openalex.org/W2105099419","https://openalex.org/W2106119541","https://openalex.org/W2121981798","https://openalex.org/W2123237149","https://openalex.org/W2146871184","https://openalex.org/W2403731734"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2162158162","https://openalex.org/W2162582511","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141"],"abstract_inverted_index":{"Recently,":[0],"several":[1],"fast":[2],"speaker":[3,10,31,50,57,95,103,118,127,183],"adaptation":[4,67,83,96,184],"methods":[5,28,68],"based":[6,51,101],"on":[7,52,102,180],"the":[8,17,29,37,42,53,91,125,164],"so-called":[9],"codes":[11,104],"(SC)":[12],"have":[13,61,89,123,150,167],"been":[14],"proposed":[15,65,126],"for":[16,157],"hybrid":[18],"DNN-HMM":[19],"speech":[20,135],"recognition":[21,136],"model":[22,99],"[1,":[23],"2,":[24],"3].":[25],"In":[26,85],"these":[27,64],"target":[30],"features":[32,108,130],"are":[33,45,69],"modified":[34],"to":[35,72],"match":[36],"given":[38],"speaker-independent":[39,43],"models":[40,44,76],"or":[41],"transformed":[46],"towards":[47],"one":[48],"particular":[49],"discriminative":[54],"learning":[55],"of":[56,82,93,117],"codes.":[58],"Previous":[59],"researches":[60],"shown":[62,168],"that":[63,152,169],"SC-based":[66],"very":[70,158],"effective":[71],"adapt":[73],"large":[74,143,159],"DNN":[75],"using":[77],"only":[78],"a":[79],"small":[80],"amount":[81],"data.":[84],"this":[86],"work,":[87],"we":[88],"explored":[90],"combination":[92],"direct":[94],"technique":[97],"in":[98,133,176],"space":[100],"(mSA-SC)":[105],"and":[106,142],"bottleneck":[107,120,129],"where":[109],"mSA-SC":[110],"is":[111,154],"used":[112],"as":[113],"an":[114,181],"extraction":[115,131],"instrument":[116],"adaptive":[119,128],"features.":[121],"We":[122],"evaluated":[124],"method":[132],"two":[134],"tasks,":[137],"namely":[138],"PSC":[139],"Mandarin":[140],"task":[141],"scale":[144,160],"320-hr":[145],"Switchboard":[146,165],"task.":[147],"Experimental":[148],"results":[149,166],"verified":[151],"it":[153,170],"quite":[155],"suitable":[156],"tasks.":[161],"For":[162],"example,":[163],"can":[171],"achieve":[172],"relative":[173],"9%":[174],"reduction":[175],"word":[177],"error":[178],"rate":[179],"unsupervised":[182],"scheme.":[185]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}