{"id":"https://openalex.org/W2697254725","doi":"https://doi.org/10.1109/icassp.2017.7953143","title":"Cumulative moving averaged bottleneck speaker vectors for online speaker adaptation of CNN-based acoustic models","display_name":"Cumulative moving averaged bottleneck speaker vectors for online speaker adaptation of CNN-based acoustic models","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2697254725","doi":"https://doi.org/10.1109/icassp.2017.7953143","mag":"2697254725"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["Graduate School of Engineering, Doshisha University, Kyoto, Japan","NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112536171","display_name":"Taichi Asami","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taichi Asami","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Yokosuka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeru Katagiri","raw_affiliation_strings":["Graduate School of Engineering, Doshisha University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Doshisha University, Kyoto, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5175","last_page":"5179"},"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":0.9994000196456909,"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":0.9991999864578247,"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":0.8116323947906494},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7417114973068237},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7002177834510803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6306797862052917},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5277912020683289},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4766174852848053},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4738926291465759},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.453704297542572},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4329664707183838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3534083962440491},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1056179404258728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116323947906494},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7417114973068237},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7002177834510803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6306797862052917},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5277912020683289},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4766174852848053},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4738926291465759},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.453704297542572},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4329664707183838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3534083962440491},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1056179404258728},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1592672653","https://openalex.org/W1608667326","https://openalex.org/W1984570643","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2015633636","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2079623482","https://openalex.org/W2095705004","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2289394825","https://openalex.org/W2398776621","https://openalex.org/W2402201734","https://openalex.org/W2404568753","https://openalex.org/W2405505124","https://openalex.org/W2514021858","https://openalex.org/W6631362777","https://openalex.org/W6674330103","https://openalex.org/W6713383670","https://openalex.org/W6713570806"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W2595172197","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2084856301"],"abstract_inverted_index":{"Adapting":[0],"acoustic":[1,105],"models":[2],"to":[3,7,74,90,111],"speakers":[4,22],"have":[5],"shown":[6],"greatly":[8],"improve":[9],"performance":[10],"for":[11,102],"many":[12],"tasks.":[13],"Among":[14],"the":[15,48,70,113,119,124],"adaptation":[16,35,73],"approaches,":[17],"exploiting":[18],"auxiliary":[19,49,71,79,114],"features":[20,50,80],"characterizing":[21],"or":[23],"environments":[24],"has":[25],"received":[26],"great":[27],"attention":[28],"because":[29],"they":[30],"allow":[31],"rapid":[32],"adaptation,":[33],"i.e.":[34],"with":[36],"limited":[37],"amount":[38],"of":[39,69],"speech":[40],"data":[41],"such":[42],"as":[43],"a":[44],"single":[45],"utterance.":[46],"However,":[47],"are":[51],"usually":[52],"computed":[53],"in":[54],"batch":[55],"mode,":[56],"which":[57],"causes":[58],"some":[59],"inevitable":[60],"latency.":[61],"In":[62],"this":[63],"paper":[64],"we":[65],"explore":[66],"an":[67],"extension":[68],"feature-based":[72],"online":[75,91,129],"processing.":[76],"We":[77,97],"employ":[78],"obtained":[81],"from":[82],"bottleneck":[83],"speaker":[84,130],"vectors":[85],"and":[86],"extend":[87],"their":[88],"computation":[89],"processing":[92],"using":[93,107],"cumulative":[94],"moving":[95],"averaging.":[96],"test":[98],"our":[99],"proposed":[100,125],"approach":[101,126],"deep":[103],"CNN-based":[104],"models,":[106],"context":[108],"adaptive":[109],"networks":[110],"exploit":[112],"features.":[115],"Experimental":[116],"results":[117],"on":[118],"CHiME-3":[120],"task":[121],"demonstrate":[122],"that":[123],"can":[127],"realize":[128],"adaptation.":[131]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}