{"id":"https://openalex.org/W2767754137","doi":"https://doi.org/10.1109/icassp.2018.8461684","title":"Unsupervised Learning of Semantic Audio Representations","display_name":"Unsupervised Learning of Semantic Audio Representations","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2767754137","doi":"https://doi.org/10.1109/icassp.2018.8461684","mag":"2767754137"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5103622427","display_name":"Aren Jansen","orcid":null},"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":true,"raw_author_name":"Aren Jansen","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059222327","display_name":"Manoj Plakal","orcid":"https://orcid.org/0000-0001-6759-3873"},"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":"Manoj Plakal","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055631690","display_name":"Ratheet Pandya","orcid":null},"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":"Ratheet Pandya","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"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":"Daniel P. W. Ellis","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014428891","display_name":"Shawn Hershey","orcid":null},"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":"Shawn Hershey","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103326319","display_name":"Jiayang Liu","orcid":null},"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":"Jiayang Liu","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110435728","display_name":"Robert C. Moore","orcid":null},"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":"R. Channing Moore","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026650852","display_name":"Rif A. Saurous","orcid":null},"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":"Rif A. Saurous","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103622427"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":13.2114,"has_fulltext":false,"cited_by_count":113,"citation_normalized_percentile":{"value":0.99211032,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919000267982483,"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":0.7619246244430542},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6873058080673218},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6374527215957642},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6220605373382568},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5328230261802673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5147731304168701},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46997302770614624},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44951558113098145},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4492916464805603},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4245033264160156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39079752564430237},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3468197286128998},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2586688995361328},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10160666704177856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619246244430542},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6873058080673218},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6374527215957642},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6220605373382568},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5328230261802673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5147731304168701},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46997302770614624},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44951558113098145},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4492916464805603},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4245033264160156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39079752564430237},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3468197286128998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2586688995361328},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10160666704177856},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/icassp.2018.8461684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W343636949","https://openalex.org/W1520997877","https://openalex.org/W1531663008","https://openalex.org/W1545920196","https://openalex.org/W1967924372","https://openalex.org/W1975517671","https://openalex.org/W2052697931","https://openalex.org/W2096733369","https://openalex.org/W2106053110","https://openalex.org/W2107789863","https://openalex.org/W2136655611","https://openalex.org/W2190506272","https://openalex.org/W2250874882","https://openalex.org/W2326925005","https://openalex.org/W2342547278","https://openalex.org/W2516890051","https://openalex.org/W2526050071","https://openalex.org/W2556930864","https://openalex.org/W2561826558","https://openalex.org/W2591013610","https://openalex.org/W2618269622","https://openalex.org/W2786608204","https://openalex.org/W2844632039","https://openalex.org/W2846592055","https://openalex.org/W2963420272","https://openalex.org/W2963775347","https://openalex.org/W2964001192","https://openalex.org/W3104866538","https://openalex.org/W4293665662","https://openalex.org/W6631829595","https://openalex.org/W6632653590","https://openalex.org/W6663645435","https://openalex.org/W6675751002","https://openalex.org/W6676071220","https://openalex.org/W6691725507","https://openalex.org/W6701655646","https://openalex.org/W6729831399","https://openalex.org/W6729977899","https://openalex.org/W6738531280","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Even":[0],"in":[1,40,68,147],"the":[2,19,45,57,60,64,76,118,127,154],"absence":[3],"of":[4,11,22,52,59,66,108,117,126,129],"any":[5],"explicit":[6],"semantic":[7,28],"annotation,":[8],"vast":[9],"collections":[10],"audio":[12],"recordings":[13],"provide":[14],"valuable":[15],"information":[16],"for":[17,104],"learning":[18],"categorical":[20],"structure":[21],"sounds.":[23],"We":[24],"consider":[25],"several":[26],"class-agnostic":[27],"constraints":[29,86],"that":[30,121],"apply":[31],"to":[32,74,82,99,135],"unlabeled":[33],"nonspeech":[34],"audio:":[35],"(i)":[36],"noise":[37],"and":[38,62,124,140],"translations":[39],"time":[41],"do":[42],"not":[43],"change":[44],"underlying":[46],"sound":[47,54,138,141],"category,":[48],"(ii)":[49],"a":[50],"mixture":[51],"two":[53],"events":[55,67],"inherits":[56],"categories":[58,65],"constituents,":[61],"(iii)":[63],"close":[69],"temporal":[70],"proximity":[71],"are":[72,87],"likely":[73],"be":[75,97],"same":[77],"or":[78],"related.":[79],"Without":[80],"labels":[81],"ground":[83],"them,":[84],"these":[85],"incompatible":[88],"with":[89],"classification":[90,143,156],"loss":[91],"functions.":[92],"However,":[93],"they":[94],"may":[95],"still":[96],"leveraged":[98],"identify":[100],"geometric":[101],"inequalities":[102],"needed":[103],"triplet":[105],"loss-based":[106],"training":[107],"convolutional":[109],"neural":[110],"networks.":[111],"The":[112],"result":[113],"is":[114],"low-dimensional":[115],"embeddings":[116,152],"input":[119],"spectrograms":[120],"recover":[122],"41%":[123],"84%":[125],"performance":[128],"their":[130],"fully-supervised":[131],"counterparts":[132],"when":[133],"applied":[134],"downstream":[136],"query-by-example":[137],"retrieval":[139],"event":[142],"tasks,":[144],"respectively.":[145],"Moreover,":[146],"limited-supervision":[148],"settings,":[149],"our":[150],"unsupervised":[151],"double":[153],"state-of-the-art":[155],"performance.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}