{"id":"https://openalex.org/W4400579199","doi":"https://doi.org/10.1109/taslp.2024.3426301","title":"From Raw Speech to Fixed Representations: A Comprehensive Evaluation of Speech Embedding Techniques","display_name":"From Raw Speech to Fixed Representations: A Comprehensive Evaluation of Speech Embedding Techniques","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400579199","doi":"https://doi.org/10.1109/taslp.2024.3426301"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3426301","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426301","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2024.3426301","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052292328","display_name":"Dejan Porjazovski","orcid":"https://orcid.org/0000-0002-7219-9042"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Dejan Porjazovski","raw_affiliation_strings":["Department of Information and Communications Engineering, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7219-9042","affiliations":[{"raw_affiliation_string":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Gr\u00f3sz","raw_affiliation_strings":["Department of Information and Communications Engineering, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-7918-9579","affiliations":[{"raw_affiliation_string":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Department of Information and Communications Engineering, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-5278-7974","affiliations":[{"raw_affiliation_string":"Department of Information and Communications Engineering, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052292328"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.9934,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79510208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"3546","last_page":"3560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/embedding","display_name":"Embedding","score":0.743437647819519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7409701347351074},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6582016944885254},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.481655478477478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46567198634147644},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4537501633167267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41434749960899353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3695601224899292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3689712882041931}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.743437647819519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409701347351074},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6582016944885254},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.481655478477478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46567198634147644},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4537501633167267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41434749960899353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3695601224899292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3689712882041931},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3426301","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426301","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/129682","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/77ebb9d7-c792-43c2-90eb-9fd413307172","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3426301","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426301","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1536121294","display_name":"Common Language Resources and Technology Infrastructure","funder_award_id":"337073","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G3490526257","display_name":null,"funder_award_id":"337073","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W1614298861","https://openalex.org/W2064675550","https://openalex.org/W2100649405","https://openalex.org/W2106885423","https://openalex.org/W2125222651","https://openalex.org/W2146334809","https://openalex.org/W2171590421","https://openalex.org/W2190506272","https://openalex.org/W2407151108","https://openalex.org/W2526050071","https://openalex.org/W2792764867","https://openalex.org/W2806021948","https://openalex.org/W2810556878","https://openalex.org/W2882319491","https://openalex.org/W2884305338","https://openalex.org/W2889326414","https://openalex.org/W2916113431","https://openalex.org/W2962736743","https://openalex.org/W2963288440","https://openalex.org/W2963317665","https://openalex.org/W2963425185","https://openalex.org/W2963571336","https://openalex.org/W2972824267","https://openalex.org/W2990374210","https://openalex.org/W2997574889","https://openalex.org/W3044967013","https://openalex.org/W3095552229","https://openalex.org/W3096196861","https://openalex.org/W3138521398","https://openalex.org/W3163379884","https://openalex.org/W3197230135","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4226380987","https://openalex.org/W4281492411","https://openalex.org/W4292457883","https://openalex.org/W4292947562","https://openalex.org/W4296068833","https://openalex.org/W4304087162","https://openalex.org/W4375869259","https://openalex.org/W4385245566","https://openalex.org/W4385247697","https://openalex.org/W4385822439","https://openalex.org/W4385823338","https://openalex.org/W4387815010","https://openalex.org/W4387968410","https://openalex.org/W4388118934","https://openalex.org/W6631362777","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6681096077","https://openalex.org/W6723250868","https://openalex.org/W6731763572","https://openalex.org/W6734194636","https://openalex.org/W6747808108","https://openalex.org/W6749825310","https://openalex.org/W6750615492","https://openalex.org/W6755207826","https://openalex.org/W6771467084","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6785591002","https://openalex.org/W6785715630","https://openalex.org/W6798110199","https://openalex.org/W6803378298","https://openalex.org/W6841896622","https://openalex.org/W7073913789"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Speech":[0],"embeddings,":[1,201],"fixed-size":[2],"representations":[3],"derived":[4],"from":[5],"raw":[6],"audio":[7],"data,":[8],"play":[9],"a":[10,68,160],"crucial":[11,174],"role":[12],"in":[13,59,80,187,206],"diverse":[14],"machine":[15],"learning":[16],"applications.":[17,165,212],"Despite":[18],"the":[19,26,47,60,96,118,123,133,137,172,176,196],"abundance":[20],"of":[21,71,136,199],"speech":[22,53,76,200],"embedding":[23,54,77],"techniques,":[24],"selecting":[25,171],"most":[27,173],"suitable":[28],"one":[29],"remains":[30],"challenging.":[31],"Existing":[32],"studies":[33],"often":[34,179],"focus":[35],"on":[36],"intrinsic":[37,87,92],"or":[38],"extrinsic":[39,89,119],"aspects,":[40],"seldom":[41],"exploring":[42],"both":[43,72,86],"simultaneously.":[44],"Furthermore,":[45,166],"comparing":[46],"state-of-the-art":[48],"pre-trained":[49,139],"models":[50,124,150],"with":[51],"prior":[52],"solutions":[55],"is":[56],"notably":[57],"scarce":[58],"literature.":[61],"To":[62],"address":[63],"these":[64],"gaps,":[65],"we":[66,167],"undertake":[67],"comprehensive":[69],"evaluation":[70],"small":[73],"and":[74,88,103,114,184,204],"large-scale":[75,138],"models,":[78,140],"which,":[79],"our":[81],"opinion,":[82],"needs":[83],"to":[84,99,154],"incorporate":[85],"assessments.":[90],"The":[91,130,147],"experiments":[93,120],"delve":[94],"into":[95,110,195],"models'":[97,177],"ability":[98],"pick":[100],"speaker-related":[101],"characteristics":[102],"assess":[104],"their":[105,111,155],"discriminative":[106],"capacities,":[107],"providing":[108],"insights":[109,194],"inherent":[112],"capabilities":[113],"internal":[115],"workings.":[116],"Concurrently,":[117],"evaluate":[121],"whether":[122],"learned":[125],"semantic":[126],"cues":[127],"during":[128],"pre-training.":[129],"findings":[131],"underscore":[132],"superior":[134],"performance":[135,178],"albeit":[141],"at":[142],"an":[143],"elevated":[144],"computational":[145],"cost.":[146],"base":[148],"self-supervised":[149],"show":[151,168],"comparable":[152],"results":[153],"large":[156],"counterparts,":[157],"making":[158,207],"them":[159],"better":[161],"choice":[162],"for":[163,210],"many":[164],"that":[169],"by":[170],"dimensions,":[175],"does":[180],"not":[181],"suffer":[182],"drastically":[183],"even":[185],"improves":[186],"some":[188],"cases.":[189],"This":[190],"research":[191],"contributes":[192],"valuable":[193],"nuanced":[197],"landscape":[198],"aiding":[202],"researchers":[203],"practitioners":[205],"informed":[208],"choices":[209],"various":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}