{"id":"https://openalex.org/W4225297336","doi":"https://doi.org/10.1109/icassp43922.2022.9747756","title":"Towards A Common Speech Analysis Engine","display_name":"Towards A Common Speech Analysis Engine","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225297336","doi":"https://doi.org/10.1109/icassp43922.2022.9747756"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747756","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"https://openalex.org/A5021900623","display_name":"Hagai Aronowitz","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hagai Aronowitz","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028984453","display_name":"Itai Gat","orcid":"https://orcid.org/0000-0002-3467-9061"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Itai Gat","raw_affiliation_strings":["IBM Research AI","Technion - Israel Institute of Technology"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]},{"raw_affiliation_string":"Technion - Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edmilson Morais","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551993","display_name":"Weizhong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhong Zhu","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021900623"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4155,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5538677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8162","last_page":"8166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.8413041830062866},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7217079401016235},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.607825517654419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5375492572784424},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5237555503845215},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4978904724121094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4739023745059967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4603900611400604},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.42070651054382324},{"id":"https://openalex.org/keywords/external-data-representation","display_name":"External Data Representation","score":0.4206762909889221},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.412044882774353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.338974267244339},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.31278786063194275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413041830062866},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7217079401016235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.607825517654419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5375492572784424},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5237555503845215},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4978904724121094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4739023745059967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4603900611400604},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.42070651054382324},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.4206762909889221},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.412044882774353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.338974267244339},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31278786063194275},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747756","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1563654090","https://openalex.org/W2146334809","https://openalex.org/W2889374687","https://openalex.org/W2896457183","https://openalex.org/W2963173418","https://openalex.org/W2963371159","https://openalex.org/W2973049979","https://openalex.org/W2973181312","https://openalex.org/W3006926732","https://openalex.org/W3015267357","https://openalex.org/W3015988193","https://openalex.org/W3024583412","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3095334805","https://openalex.org/W3095789936","https://openalex.org/W3096147072","https://openalex.org/W3180180466","https://openalex.org/W3197156295","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198016157","https://openalex.org/W3198429080","https://openalex.org/W3198528147","https://openalex.org/W3198614662","https://openalex.org/W3198668286","https://openalex.org/W3209059054","https://openalex.org/W6749107692","https://openalex.org/W6755207826","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W134179020","https://openalex.org/W3107456284","https://openalex.org/W2099475353","https://openalex.org/W2184127972","https://openalex.org/W2389353568","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W596245619","https://openalex.org/W2320148263","https://openalex.org/W2008120082"],"abstract_inverted_index":{"Recent":[0],"innovations":[1],"in":[2,11,17,35],"self-supervised":[3,22,109],"representation":[4,23],"learning":[5],"have":[6],"led":[7],"to":[8,39,52,62,163],"remarkable":[9],"advances":[10,34],"natural":[12],"language":[13,120],"processing.":[14],"That":[15],"said,":[16],"the":[18,97,107,126,136,150],"speech":[19,37,43,55,102,110],"processing":[20,38,56],"domain,":[21],"learning-based":[24],"systems":[25],"are":[26],"not":[27],"yet":[28],"considered":[29],"state-of-the-art.We":[30],"propose":[31],"leveraging":[32],"recent":[33],"self-supervised-based":[36],"create":[40],"a":[41,59,81,100],"common":[42,82,101],"analysis":[44,103],"engine.":[45],"Such":[46],"an":[47],"engine":[48,67,83,104,148],"should":[49,84],"be":[50,85],"able":[51],"handle":[53],"multiple":[54],"tasks,":[57],"using":[58,154],"single":[60],"architecture,":[61],"obtain":[63],"state-of-the-art":[64,137],"accuracy.":[65],"The":[66],"must":[68],"also":[69,145],"enable":[70],"support":[71],"for":[72,99,119],"new":[73],"tasks":[74],"with":[75,91],"small":[76],"training":[77,90,158],"datasets.":[78],"Beyond":[79],"that,":[80],"capable":[86],"of":[87,157],"supporting":[88],"distributed":[89],"client":[92],"in-house":[93],"private":[94],"data.We":[95],"present":[96],"architecture":[98],"based":[105],"on":[106,113,125,142,149],"HuBERT":[108],"representation.":[111],"Based":[112],"experiments,":[114],"we":[115],"report":[116],"our":[117,147],"results":[118,134],"identification":[121],"and":[122,131,160],"emotion":[123,151],"recognition":[124,152],"standard":[127],"evaluations":[128],"NIST-LRE":[129],"07":[130],"IEMOCAP.":[132],"Our":[133],"surpass":[135],"performance":[138],"reported":[139],"so":[140],"far":[141],"these":[143],"tasks.We":[144],"analyzed":[146],"task":[153],"reduced":[155],"amounts":[156],"data":[159],"show":[161],"how":[162],"achieve":[164],"improved":[165],"results.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}