{"id":"https://openalex.org/W4308480316","doi":"https://doi.org/10.1109/jstsp.2022.3205434","title":"Editorial Editorial of Special Issue on Self-Supervised Learning for Speech and Audio Processing","display_name":"Editorial Editorial of Special Issue on Self-Supervised Learning for Speech and Audio Processing","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4308480316","doi":"https://doi.org/10.1109/jstsp.2022.3205434"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3205434","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3205434","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09923629.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"editorial","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09923629.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["TTI-Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TTI-Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101170706","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelrahman Mohamed","raw_affiliation_strings":["Fundamental AI Research (FAIR), Meta, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundamental AI Research (FAIR), Meta, Seattle, WA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara Sainath","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4126-6556","affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"6","first_page":"1174","last_page":"1178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9559000134468079,"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":0.9559000134468079,"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":0.8236796855926514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5692122578620911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.559808075428009},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5424386858940125},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5159454941749573},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4828815758228302},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4622058868408203},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4615173041820526},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4599300026893616},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44585633277893066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.387564480304718},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3574877977371216},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21801620721817017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8236796855926514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5692122578620911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.559808075428009},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5424386858940125},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5159454941749573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4828815758228302},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4622058868408203},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4615173041820526},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4599300026893616},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44585633277893066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.387564480304718},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3574877977371216},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21801620721817017},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3205434","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3205434","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09923629.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/jstsp.2022.3205434","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3205434","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09923629.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308480316.pdf","grobid_xml":"https://content.openalex.org/works/W4308480316.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W3039695075","https://openalex.org/W3134652006","https://openalex.org/W3136810184","https://openalex.org/W3144173820","https://openalex.org/W3157923770","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3197580070","https://openalex.org/W3198771897","https://openalex.org/W3204696009","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4221140961","https://openalex.org/W4221141236","https://openalex.org/W4221152601","https://openalex.org/W4221160587","https://openalex.org/W4221161753","https://openalex.org/W4280619727","https://openalex.org/W4281492411","https://openalex.org/W4281663607","https://openalex.org/W4285069952","https://openalex.org/W4285110637","https://openalex.org/W4285144981","https://openalex.org/W4285192675","https://openalex.org/W4285225028","https://openalex.org/W4285258106","https://openalex.org/W4285412695","https://openalex.org/W4285414370","https://openalex.org/W4285821318","https://openalex.org/W4286359908","https://openalex.org/W4287889585","https://openalex.org/W4289792473","https://openalex.org/W4289821214","https://openalex.org/W4289824098","https://openalex.org/W4290712827","https://openalex.org/W4290995108","https://openalex.org/W4292825791","https://openalex.org/W4292968575","https://openalex.org/W4292969786","https://openalex.org/W4292976050","https://openalex.org/W4293370787","https://openalex.org/W4293793697","https://openalex.org/W4294068504","https://openalex.org/W4295308567","https://openalex.org/W4402490925","https://openalex.org/W6779941907"],"related_works":["https://openalex.org/W3162567751","https://openalex.org/W3210156800","https://openalex.org/W4220686584","https://openalex.org/W4246751904","https://openalex.org/W4226172683","https://openalex.org/W2795261237","https://openalex.org/W2597787948","https://openalex.org/W2295628041","https://openalex.org/W2908875379","https://openalex.org/W4308480316"],"abstract_inverted_index":{"The":[0],"papers":[1],"in":[2,18],"this":[3],"special":[4],"section":[5],"focus":[6],"on":[7,57,80],"self-supervised":[8,27,89],"learning":[9,21,34,37],"for":[10,91],"speech":[11,92],"and":[12,93],"audio":[13,94],"processing.":[14],"A":[15],"current":[16],"trend":[17],"the":[19,24,46,73,81],"machine":[20],"community":[22],"is":[23],"adoption":[25],"of":[26,45,76],"approaches":[28,67,90],"to":[29,71,83],"pretrain":[30],"deep":[31],"networks.":[32],"Self-supervised":[33],"utilizes":[35],"proxy-supervised":[36],"tasks":[38],"(or":[39],"pretext":[40],"tasks)\u2014for":[41],"example,":[42],"distinguishing":[43],"parts":[44],"input":[47,54],"signal":[48],"from":[49,63],"distractors":[50],"or":[51],"reconstructing":[52],"masked":[53],"segments":[55],"conditioned":[56],"unmasked":[58],"segments\u2014to":[59],"obtain":[60],"training":[61],"data":[62,78],"unlabeled":[64,77],"corpora.":[65],"These":[66],"make":[68],"it":[69],"possible":[70],"use":[72],"tremendous":[74],"amount":[75],"available":[79],"web":[82],"train":[84],"large":[85],"neural":[86],"models.":[87],"Recent":[88],"processing":[95],"are":[96],"also":[97],"gaining":[98],"attention.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}