{"id":"https://openalex.org/W3015295955","doi":"https://doi.org/10.1109/icassp40776.2020.9053150","title":"A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification","display_name":"A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015295955","doi":"https://doi.org/10.1109/icassp40776.2020.9053150","mag":"3015295955"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":["Amazon.com Inc"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Amazon.com Inc"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["Salesforce Research"],"affiliations":[{"raw_affiliation_string":"Salesforce Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"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/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon.com Inc"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020775828"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":3.4853,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93423305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"320"},"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":0.9990000128746033,"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":0.9976999759674072,"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/pooling","display_name":"Pooling","score":0.7837674617767334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7738364934921265},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7506712675094604},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7155359983444214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5827985405921936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5807937383651733},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.552570104598999},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5018999576568604},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48746180534362793},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41556575894355774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4029550552368164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3857567310333252},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06890672445297241}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7837674617767334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738364934921265},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7506712675094604},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7155359983444214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827985405921936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5807937383651733},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.552570104598999},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5018999576568604},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48746180534362793},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41556575894355774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4029550552368164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3857567310333252},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06890672445297241},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"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":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1909234690","https://openalex.org/W2064675550","https://openalex.org/W2099968322","https://openalex.org/W2135131618","https://openalex.org/W2140647972","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2341412280","https://openalex.org/W2402268235","https://openalex.org/W2403757143","https://openalex.org/W2407005679","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2602634800","https://openalex.org/W2745969942","https://openalex.org/W2746554716","https://openalex.org/W2775505379","https://openalex.org/W2888283879","https://openalex.org/W2889933531","https://openalex.org/W2907106536","https://openalex.org/W2939302994","https://openalex.org/W2953092061","https://openalex.org/W2953219395","https://openalex.org/W2963610932","https://openalex.org/W2964066126","https://openalex.org/W2964121744","https://openalex.org/W2964255864","https://openalex.org/W2964347220","https://openalex.org/W2972384212","https://openalex.org/W2972651776","https://openalex.org/W4288573105","https://openalex.org/W6631190155","https://openalex.org/W6747331233","https://openalex.org/W6757067665","https://openalex.org/W6759470717"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2770764537"],"abstract_inverted_index":{"Acoustic":[0],"event":[1,6,104,152],"classification":[2,99,147],"(AEC)":[3],"and":[4,69,149],"acoustic":[5],"detection":[7,118],"(AED)":[8],"refer":[9],"to":[10,28,103,135,151],"the":[11,52,114,117,132,137,140,163],"task":[12],"of":[13,54,72,85,119,146,166],"detecting":[14],"whether":[15],"specific":[16],"target":[17],"events":[18,87,122],"occur":[19],"in":[20,31,144],"audios.":[21],"As":[22],"long":[23],"short-term":[24],"memory":[25,67],"(LSTM)":[26],"leads":[27],"state-of-the-art":[29],"results":[30],"various":[32],"speech":[33],"related":[34],"tasks,":[35],"it":[36],"is":[37,111,162],"employed":[38],"as":[39,45],"a":[40,62,70],"popular":[41],"solution":[42],"for":[43,116,173],"AEC":[44,58,174],"well.":[46],"This":[47,92],"paper":[48,93],"focuses":[49,94],"on":[50,57,65,77,95,113,131,170],"investigating":[51],"dynamics":[53,172],"LSTM":[55,66,78,171],"model":[56],"tasks.":[59,175],"It":[60],"includes":[61],"detailed":[63],"analysis":[64,110],"retaining,":[68],"benchmarking":[71],"nine":[73,141],"different":[74,89],"pooling":[75,130,142],"methods":[76],"models":[79],"using":[80],"1.7M":[81],"generated":[82],"mixture":[83],"clips":[84],"multiple":[86],"with":[88],"signal-to-noise":[90],"ratios.":[91],"understanding:":[96],"1)":[97],"utterance-level":[98],"accuracy;":[100],"2)":[101],"sensitivity":[102],"position":[105,153],"within":[106,154],"an":[107,155],"utterance.":[108,156],"The":[109],"done":[112],"dataset":[115],"rare":[120],"sound":[121],"from":[123],"DCASE":[124],"2017":[125],"Challenge.":[126],"We":[127],"find":[128],"max":[129],"prediction":[133],"level":[134],"perform":[136],"best":[138,159],"among":[139],"approaches":[143],"terms":[145],"accuracy":[148],"insensitivity":[150],"To":[157],"authors\u2019":[158],"knowledge,":[160],"this":[161],"first":[164],"kind":[165],"such":[167],"work":[168],"focused":[169]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}