{"id":"https://openalex.org/W2404901536","doi":"https://doi.org/10.21437/interspeech.2014-503","title":"Speaker adaptation of DNN-based ASR with i-vectors: does it actually adapt models to speakers?","display_name":"Speaker adaptation of DNN-based ASR with i-vectors: does it actually adapt models to speakers?","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2404901536","doi":"https://doi.org/10.21437/interspeech.2014-503","mag":"2404901536"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5071001941","display_name":"Micka\u00ebl Rouvier","orcid":"https://orcid.org/0000-0003-3541-3385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mickael Rouvier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071505335","display_name":"Beno\u00eet Favre","orcid":"https://orcid.org/0000-0002-9777-4613"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benoit Favre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3007","last_page":"3011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908999800682068,"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":0.9908999800682068,"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":0.9517999887466431,"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/T12031","display_name":"Speech and dialogue systems","score":0.9509000182151794,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925779223442078},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7551968097686768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6874253153800964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3375943601131439},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33066388964653015},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10479655861854553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925779223442078},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7551968097686768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6874253153800964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375943601131439},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33066388964653015},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10479655861854553},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W157724941","https://openalex.org/W163811496","https://openalex.org/W1524333225","https://openalex.org/W1589339348","https://openalex.org/W1631260214","https://openalex.org/W1989549063","https://openalex.org/W2037740282","https://openalex.org/W2054060258","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2100969003","https://openalex.org/W2106051978","https://openalex.org/W2107638917","https://openalex.org/W2147768505","https://openalex.org/W2394932179","https://openalex.org/W2395069802","https://openalex.org/W2395750323","https://openalex.org/W2397474108","https://openalex.org/W2401027203","https://openalex.org/W2406312423","https://openalex.org/W2406500670"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNN)":[3],"are":[4],"currently":[5],"very":[6,34],"successful":[7],"for":[8],"acoustic":[9,66,89,113,131,143],"modeling":[10],"in":[11,129],"ASR":[12],"systems.":[13],"One":[14],"of":[15,37,57,79,119],"the":[16,55,61],"main":[17],"challenges":[18],"with":[19,64,88,111],"DNNs":[20,31,47,84,105],"is":[21,81,95,133],"unsupervised":[22],"speaker":[23,28,137],"adaptation":[24,80,141],"from":[25],"an":[26],"initial":[27],"clustering,":[29],"because":[30],"have":[32],"a":[33,40,117],"large":[35],"number":[36],"parameters.":[38],"Recently,":[39],"method":[41],"has":[42],"been":[43],"proposed":[44],"to":[45,48,73,116,142],"adapt":[46],"speakers":[49],"by":[50,97],"combining":[51],"speaker-specific":[52],"information":[53,93],"(in":[54],"form":[56],"i-vectors":[58,87],"computed":[59],"at":[60],"speaker-cluster":[62],"level)":[63],"fMLLR-transformed":[65,112],"features.":[67],"In":[68],"this":[69],"paper":[70],"we":[71],"try":[72],"gain":[74,118],"insight":[75],"on":[76,83,101,107],"what":[77,92],"kind":[78],"performed":[82],"when":[85],"stacking":[86,128],"features":[90,109,114],"and":[91],"exactly":[94],"carried":[96],"i-vectors.":[98],"We":[99],"observe":[100],"REPERE":[102],"corpus":[103],"that":[104,125],"trained":[106],"i-vector":[108],"concatenated":[110],"lead":[115],"0.7":[120],"points.":[121],"The":[122],"experiments":[123],"shows":[124],"using":[126],"ivector":[127],"DNN":[130],"models":[132],"not":[134],"only":[135],"performing":[136],"adaptation,":[138],"but":[139],"also":[140],"conditions.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}