{"id":"https://openalex.org/W4392904670","doi":"https://doi.org/10.1109/icassp48485.2024.10447222","title":"Streaming Anchor Loss: Augmenting Supervision with Temporal Significance","display_name":"Streaming Anchor Loss: Augmenting Supervision with Temporal Significance","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904670","doi":"https://doi.org/10.1109/icassp48485.2024.10447222"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447222","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016137147","display_name":"Utkarsh Sarawgi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Utkarsh Oggy Sarawgi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054478787","display_name":"John Berkowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Berkowitz","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083789644","display_name":"Vineet Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vineet Garg","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034953394","display_name":"Arnav Kundu","orcid":"https://orcid.org/0000-0003-2921-4312"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arnav Kundu","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076654","display_name":"Minsik Cho","orcid":"https://orcid.org/0000-0003-0481-2682"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minsik Cho","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079363821","display_name":"Sai Srujana Buddi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sai Srujana Buddi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068392026","display_name":"Saurabh Adya","orcid":"https://orcid.org/0009-0000-4533-6577"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saurabh Adya","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089360428","display_name":"Ahmed H. Tewfik","orcid":"https://orcid.org/0000-0002-2384-4391"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahmed Tewfik","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"6110","last_page":"6114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8448635339736938},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6787344813346863},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5930935740470886},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5553544759750366},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5484257340431213},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5304871201515198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45329779386520386},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.43609383702278137},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.4348510205745697},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4201204478740692},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.41747069358825684},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.40697455406188965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3918694853782654},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3501136302947998},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3339311480522156},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.25140267610549927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448635339736938},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6787344813346863},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5930935740470886},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5553544759750366},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5484257340431213},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5304871201515198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45329779386520386},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43609383702278137},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.4348510205745697},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4201204478740692},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.41747069358825684},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.40697455406188965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3918694853782654},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3501136302947998},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3339311480522156},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.25140267610549927},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447222","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2073241381","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2949738301","https://openalex.org/W2963351448","https://openalex.org/W2963414781","https://openalex.org/W2991349609","https://openalex.org/W2991403827","https://openalex.org/W2997967197","https://openalex.org/W3016010032","https://openalex.org/W3095738426","https://openalex.org/W3096831963","https://openalex.org/W3103611212","https://openalex.org/W3119038403","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3160056314","https://openalex.org/W3163074978","https://openalex.org/W3168227666","https://openalex.org/W3196296753","https://openalex.org/W3198850376","https://openalex.org/W4224926630","https://openalex.org/W4303649029","https://openalex.org/W4385822376","https://openalex.org/W6770362605","https://openalex.org/W7053361214"],"related_works":["https://openalex.org/W3161425572","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690","https://openalex.org/W4387583836"],"abstract_inverted_index":{"Streaming":[0,54],"neural":[1],"network":[2],"models":[3,28],"for":[4,43,106],"fast":[5],"frame-wise":[6,86],"responses":[7],"to":[8,34,58,69,156],"various":[9],"speech":[10,146],"and":[11,79,139,166],"sensory":[12],"signals":[13],"are":[14],"widely":[15],"adopted":[16],"on":[17,91,125,143],"resource-constrained":[18],"platforms.":[19],"Hence,":[20],"increasing":[21],"the":[22,36,61,67,85,92,95,109,121,127,154,158],"learning":[23,63],"capacity":[24,64],"of":[25,94,112],"such":[26],"streaming":[27,141],"(i.e.,":[29],"by":[30,65],"adding":[31],"more":[32,71,161],"parameters)":[33],"improve":[35],"predictive":[37],"power":[38],"may":[39],"not":[40],"be":[41],"viable":[42],"real-world":[44],"tasks.":[45],"In":[46],"this":[47],"work,":[48],"we":[49],"propose":[50],"a":[51,100],"new":[52],"loss,":[53],"Anchor":[55],"Loss":[56],"(SAL),":[57],"better":[59],"utilize":[60],"given":[62],"encouraging":[66],"model":[68,122,155,172],"learn":[70,157],"from":[72],"essential":[73],"frames.":[74,132],"More":[75],"specifically,":[76],"our":[77,117],"SAL":[78,152],"its":[80],"focal":[81],"variations":[82],"dynamically":[83],"modulate":[84],"cross":[87],"entropy":[88],"loss":[89,102,118],"based":[90,147],"importance":[93],"corresponding":[96],"frames":[97,107],"so":[98],"that":[99,120,151],"higher":[101],"penalty":[103],"is":[104],"assigned":[105],"within":[108],"temporal":[110],"proximity":[111],"semantically":[113],"critical":[114],"events.":[115],"Therefore,":[116],"ensures":[119],"training":[123],"focuses":[124],"predicting":[126],"relatively":[128],"rare":[129],"but":[130],"task-relevant":[131],"Experimental":[133],"results":[134],"with":[135,163],"standard":[136],"lightweight":[137],"convolutional":[138],"recurrent":[140],"networks":[142],"three":[144],"different":[145],"detection":[148],"tasks":[149],"demonstrate":[150],"enables":[153],"overall":[159],"task":[160],"effectively":[162],"improved":[164],"accuracy":[165],"latency,":[167],"without":[168],"any":[169],"additional":[170],"data,":[171],"parameters,":[173],"or":[174],"architectural":[175],"changes.":[176]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}