{"id":"https://openalex.org/W3095385545","doi":"https://doi.org/10.21437/interspeech.2020-2835","title":"Intra-Utterance Similarity Preserving Knowledge Distillation for Audio Tagging","display_name":"Intra-Utterance Similarity Preserving Knowledge Distillation for Audio Tagging","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095385545","doi":"https://doi.org/10.21437/interspeech.2020-2835","mag":"3095385545"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2835","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5101482345","display_name":"Chun\u2010Chieh Chang","orcid":"https://orcid.org/0009-0005-9109-4034"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Chieh Chang","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[{"id":"https://openalex.org/I2802722262","display_name":"Bibliotheca Alexandrina","ror":"https://ror.org/051a9ap09","country_code":"EG","type":"archive","lineage":["https://openalex.org/I2802722262"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":["Alexa Speech,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Speech,","institution_ids":["https://openalex.org/I2802722262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755314","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-8625-5199"},"institutions":[{"id":"https://openalex.org/I2802722262","display_name":"Bibliotheca Alexandrina","ror":"https://ror.org/051a9ap09","country_code":"EG","type":"archive","lineage":["https://openalex.org/I2802722262"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Alexa Speech,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Speech,","institution_ids":["https://openalex.org/I2802722262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406892","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0001-7578-1970"},"institutions":[{"id":"https://openalex.org/I2802722262","display_name":"Bibliotheca Alexandrina","ror":"https://ror.org/051a9ap09","country_code":"EG","type":"archive","lineage":["https://openalex.org/I2802722262"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Alexa Speech,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Speech,","institution_ids":["https://openalex.org/I2802722262"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6083,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67662405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"851","last_page":"855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.7778406739234924},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7432857751846313},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6631706357002258},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.49986767768859863},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49718835949897766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4786749482154846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46408745646476746},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05577850341796875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778406739234924},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7432857751846313},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6631706357002258},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.49986767768859863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49718835949897766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4786749482154846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46408745646476746},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05577850341796875},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2835","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"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":22,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2341412280","https://openalex.org/W2402040300","https://openalex.org/W2508418541","https://openalex.org/W2526050071","https://openalex.org/W2561238782","https://openalex.org/W2739879705","https://openalex.org/W2938357656","https://openalex.org/W2963096935","https://openalex.org/W2963140444","https://openalex.org/W2963543871","https://openalex.org/W2963723765","https://openalex.org/W2963864497","https://openalex.org/W2972384212","https://openalex.org/W2972548957","https://openalex.org/W2982036217","https://openalex.org/W2982242214","https://openalex.org/W2982325051","https://openalex.org/W2995607862","https://openalex.org/W3118608800","https://openalex.org/W4295723153"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"Knowledge":[0],"Distillation":[1],"(KD)":[2],"is":[3,72,134],"a":[4,93,105,135],"popular":[5],"area":[6],"of":[7,13,22,32,39,85,104,121,143,153],"research":[8],"for":[9,53,67,131],"reducing":[10],"the":[11,30,36,50,68,75,87,98,102,125,147,155],"size":[12],"large":[14],"models":[15,25,120],"while":[16],"still":[17],"maintaining":[18],"good":[19],"performance.The":[20],"outputs":[21],"larger":[23],"teacher":[24],"are":[26],"used":[27],"to":[28,44,48,137,150],"guide":[29],"training":[31,52],"smaller":[33],"student":[34,119],"models.Given":[35],"repetitive":[37],"nature":[38],"acoustic":[40],"events,":[41],"we":[42],"propose":[43],"leverage":[45],"this":[46],"information":[47],"regulate":[49],"KD":[51,57,62,78,82,110],"Audio":[54],"Tagging.This":[55],"novel":[56],"method,":[58,111],"Intra-Utterance":[59],"Similarity":[60,80],"Preserving":[61,81],"(IUSP),":[63],"shows":[64,113],"promising":[65],"results":[66],"audio":[69,132],"tagging":[70],"task.It":[71],"motivated":[73],"by":[74],"previously":[76],"published":[77],"method:":[79],"(SP).However,":[83],"instead":[84],"preserving":[86],"pairwise":[88,99],"similarities":[89,100],"between":[90,101],"inputs":[91],"within":[92],"mini-batch,":[94],"our":[95],"method":[96],"preserves":[97],"frames":[103],"single":[106],"input":[107],"utterance.Our":[108],"proposed":[109],"IUSP,":[112],"consistent":[114],"improvements":[115],"over":[116,146,154],"SP":[117],"across":[118],"different":[122],"sizes":[123],"on":[124],"DCASE":[126],"2019":[127],"Task":[128],"5":[129],"dataset":[130],"tagging.There":[133],"27.1%":[136],"122.4%":[138],"percent":[139],"increase":[140],"in":[141],"improvement":[142,152],"micro":[144],"AUPRC":[145],"baseline":[148],"relative":[149],"SPs":[151],"baseline.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}