{"id":"https://openalex.org/W7148365232","doi":"https://doi.org/10.1109/asru65441.2025.11434653","title":"JOOCI: a Novel Method for Learning Comprehensive Speech Representations","display_name":"JOOCI: a Novel Method for Learning Comprehensive Speech Representations","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148365232","doi":"https://doi.org/10.1109/asru65441.2025.11434653"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Hemant Yadav","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Hemant Yadav","raw_affiliation_strings":["IIIT,Delhi,India"],"affiliations":[{"raw_affiliation_string":"IIIT,Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005513786","display_name":"Sunayana Sitaram","orcid":"https://orcid.org/0000-0003-4251-9719"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunayana Sitaram","raw_affiliation_strings":["Microsoft Research,India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research,India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132822078","display_name":"Rajiv Ratn Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":["IIIT,Delhi,India"],"affiliations":[{"raw_affiliation_string":"IIIT,Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86688003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6916999816894531,"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":0.6916999816894531,"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":0.058800000697374344,"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":0.037700001150369644,"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/feature","display_name":"Feature (linguistics)","score":0.3188999891281128},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.30570000410079956},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.26429998874664307},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.26010000705718994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6148999929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45350000262260437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6811615228652954,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2194775991","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2928165649","https://openalex.org/W2973049979","https://openalex.org/W3016181583","https://openalex.org/W3197580070","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4200633018","https://openalex.org/W4226033575","https://openalex.org/W4226278833","https://openalex.org/W4226380987","https://openalex.org/W4281492411","https://openalex.org/W4297841871","https://openalex.org/W4312933868","https://openalex.org/W4319862642","https://openalex.org/W4372267483","https://openalex.org/W4372346385","https://openalex.org/W4375869259","https://openalex.org/W4381786045","https://openalex.org/W4385484947","https://openalex.org/W4385822740","https://openalex.org/W4389518881","https://openalex.org/W4394862910","https://openalex.org/W4402111556"],"related_works":[],"abstract_inverted_index":{"Information":[0,141],"in":[1,45,51,56,135],"speech":[2,86],"can":[3,70],"be":[4],"categorized":[5],"into":[6],"two":[7,121,125],"groups:":[8],"Content":[9,57,140],"(what":[10],"is":[11,21,63],"being":[12],"said,":[13],"such":[14,23],"as":[15,24,66],"linguistics)":[16],"and":[17,28,53,107,124,139],"Other":[18,52,138],"(how":[19],"it":[20],"expressed":[22],"information":[25,68,99],"about":[26],"speaker":[27,122],"paralinguistic":[29],"features).":[30],"Current":[31],"self-supervised":[32],"learning":[33,88],"(SSL)":[34],"methods":[35],"are":[36],"shown":[37],"to":[38,74],"divide":[39],"the":[40,95,129],"model\u2019s":[41],"representational-depth":[42,96],"or":[43],"layers":[44,49,55,73],"two,":[46],"with":[47],"earlier":[48],"specializing":[50],"later":[54],"related":[58],"tasks.":[59],"This":[60],"layer-wise":[61],"division":[62],"inherently":[64],"sub-optimal,":[65],"neither":[67],"type":[69],"use":[71],"all":[72],"build":[75],"hierarchical":[76],"representations.":[77],"To":[78],"address":[79],"this,":[80],"we":[81],"propose":[82],"JOOCI,":[83],"a":[84],"novel":[85],"representation":[87],"method":[89],"that":[90],"does":[91],"not":[92],"compromise":[93],"on":[94,120],"for":[97],"either":[98],"type.":[100],"JOOCI":[101],"outperforms":[102],"WavLM":[103],"by":[104],"26.5%":[105],"(relative),":[106],"other":[108],"models":[109],"of":[110],"similar":[111],"size":[112],"($\\mathbf{1":[113],"0":[114,115],"M}$":[116],"parameters),":[117],"when":[118],"evaluated":[119],"recognition":[123],"language":[126],"tasks":[127],"from":[128],"SUPERB":[130],"benchmark,":[131],"demonstrating":[132],"its":[133],"effectiveness":[134],"Jointly":[136],"Optimizing":[137],"(JOOCI).":[142]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-03T00:00:00"}