{"id":"https://openalex.org/W4402111801","doi":"https://doi.org/10.21437/interspeech.2024-2116","title":"Reshape Dimensions Network for Speaker Recognition","display_name":"Reshape Dimensions Network for Speaker Recognition","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111801","doi":"https://doi.org/10.21437/interspeech.2024-2116"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2116","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2116","pdf_url":"https://www.isca-archive.org/interspeech_2024/yakovlev24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/yakovlev24_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038996601","display_name":"Ivan Yakovlev","orcid":"https://orcid.org/0000-0002-0291-8857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Yakovlev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090494693","display_name":"Rostislav Makarov","orcid":"https://orcid.org/0000-0002-5236-4143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rostislav Makarov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092838089","display_name":"Andrei Balykin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei Balykin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092838088","display_name":"Pavel Malov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Malov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073552733","display_name":"Anton Okhotnikov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anton Okhotnikov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055493823","display_name":"Nikita Torgashov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Torgashov","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":5.9219,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96709119,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3235","last_page":"3239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.998199999332428,"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":0.9919000267982483,"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":0.7722766399383545},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6176034212112427},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.544459879398346},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5419129133224487},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5219040513038635},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4985206127166748},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4549238085746765},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4542745053768158},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.45388728380203247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.453738808631897},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4255833327770233},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.42395684123039246},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.4230929911136627},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41216549277305603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39263132214546204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3821563124656677},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23696324229240417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7722766399383545},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6176034212112427},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.544459879398346},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5419129133224487},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5219040513038635},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4985206127166748},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4549238085746765},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4542745053768158},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.45388728380203247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.453738808631897},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4255833327770233},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.42395684123039246},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.4230929911136627},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41216549277305603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39263132214546204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3821563124656677},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23696324229240417},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-2116","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2116","pdf_url":"https://www.isca-archive.org/interspeech_2024/yakovlev24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.18223","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.18223","pdf_url":"https://arxiv.org/pdf/2407.18223","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-2116","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2116","pdf_url":"https://www.isca-archive.org/interspeech_2024/yakovlev24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111801.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W4391160746","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,74],"present":[4],"Reshape":[5],"Dimensions":[6],"Network":[7],"(ReDimNet),":[8],"a":[9,76],"novel":[10],"neural":[11],"network":[12,48],"architecture":[13],"for":[14],"extracting":[15],"utterance-level":[16],"speaker":[17,104],"representations.":[18],"Our":[19,94],"approach":[20],"leverages":[21],"dimensionality":[22],"reshaping":[23],"of":[24,39,54,57,78,113],"2D":[25,42,60],"feature":[26,65],"maps":[27,66],"to":[28,84,91],"1D":[29,40,58],"signal":[30],"representation":[31],"and":[32,41,59,73,88,110],"vice":[33],"versa,":[34],"enabling":[35],"the":[36,52,111],"joint":[37],"usage":[38],"blocks.":[43],"We":[44],"propose":[45],"an":[46],"original":[47],"topology":[49],"that":[50,98],"preserves":[51],"volume":[53],"channel-timestep-frequency":[55],"outputs":[56],"blocks,":[61],"facilitating":[62],"efficient":[63],"residual":[64],"aggregation.":[67],"Moreover,":[68],"ReDimNet":[69,99],"is":[70],"efficiently":[71],"scalable,":[72],"introduce":[75],"range":[77],"model":[79,114],"sizes,":[80],"varying":[81],"from":[82,89],"1":[83],"15":[85],"M":[86],"parameters":[87],"0.5":[90],"20":[92],"GMACs.":[93],"experimental":[95],"results":[96],"demonstrate":[97],"achieves":[100],"state-of-the-art":[101],"performance":[102],"in":[103],"recognition":[105],"while":[106],"reducing":[107],"computational":[108],"complexity":[109],"number":[112],"parameters.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":11}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}