{"id":"https://openalex.org/W2398776621","doi":"https://doi.org/10.1109/icassp.2016.7472692","title":"Sequence summarizing neural network for speaker adaptation","display_name":"Sequence summarizing neural network for speaker adaptation","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398776621","doi":"https://doi.org/10.1109/icassp.2016.7472692","mag":"2398776621"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5045351360","display_name":"Karel Vesel\u00fd","orcid":"https://orcid.org/0000-0002-3568-7493"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Karel Vesely","raw_affiliation_strings":["Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067790073","display_name":"Kate\u0159ina \u017dmol\u00edkov\u00e1","orcid":"https://orcid.org/0000-0003-4438-8580"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Katerina Zmolikova","raw_affiliation_strings":["Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00fd, CZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00fd, CZ","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Karafiat","raw_affiliation_strings":["Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00fd, CZ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00fd, CZ","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Honza Cernocky","raw_affiliation_strings":["Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.1828,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.97935647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5315","last_page":"5319"},"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":0.9932000041007996,"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":0.9896000027656555,"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":0.7474215626716614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6965962052345276},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5919361114501953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5794092416763306},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5757222175598145},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5135645866394043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5068307518959045},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4854877293109894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47980836033821106},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4293466806411743},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09365567564964294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0930507481098175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474215626716614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6965962052345276},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5919361114501953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5794092416763306},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5757222175598145},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5135645866394043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5068307518959045},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4854877293109894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47980836033821106},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4293466806411743},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09365567564964294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0930507481098175},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W2036351241","https://openalex.org/W2045317385","https://openalex.org/W2046056978","https://openalex.org/W2079623482","https://openalex.org/W2085628288","https://openalex.org/W2094147890","https://openalex.org/W2124558353","https://openalex.org/W2131342762","https://openalex.org/W2136922672","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2164240571","https://openalex.org/W2395043307","https://openalex.org/W2401812832","https://openalex.org/W2403307129","https://openalex.org/W2404568753","https://openalex.org/W2405505124","https://openalex.org/W4214784823","https://openalex.org/W6631943919","https://openalex.org/W6712113799","https://openalex.org/W6712730384","https://openalex.org/W6713383670","https://openalex.org/W6713570806","https://openalex.org/W6713726233"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,16,29],"DNN":[6,111],"adaptation":[7,66],"technique,":[8],"where":[9],"the":[10,26,45,61,91,97,106],"i-vector":[11,24,62,92],"extractor":[12],"is":[13,41],"replaced":[14],"by":[15],"Sequence":[17],"Summarizing":[18],"Neural":[19],"Network":[20],"(SSNN).":[21],"Similarly":[22],"to":[23,44,96,101,105],"extractor,":[25],"SSNN":[27,64],"produces":[28],"\"summary":[30,94],"vector\",":[31],"representing":[32],"an":[33,37],"acoustic":[34],"summary":[35],"of":[36,47,79,108],"utterance.":[38],"Such":[39],"vector":[40],"then":[42],"appended":[43],"input":[46],"main":[48],"network,":[49],"while":[50],"both":[51,80,90],"networks":[52],"are":[53,68],"trained":[54],"together":[55],"optimizing":[56],"single":[57],"loss":[58],"function.":[59],"Both":[60],"and":[63,93],"speaker":[65],"methods":[67],"compared":[69],"on":[70,82],"AMI":[71],"meeting":[72],"data.":[73],"The":[74],"results":[75],"show":[76],"comparable":[77,104],"performance":[78,107],"techniques":[81],"FBANK":[83,98],"system":[84],"with":[85],"frame-classification":[86],"training.":[87],"Moreover,":[88],"appending":[89],"vector\"":[95],"features":[99],"leads":[100],"additional":[102],"improvement":[103],"FMLLR":[109],"adapted":[110],"system.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}