{"id":"https://openalex.org/W2723513260","doi":"https://doi.org/10.1109/icassp.2017.7952259","title":"BLSTM-HMM hybrid system combined with sound activity detection network for polyphonic Sound Event Detection","display_name":"BLSTM-HMM hybrid system combined with sound activity detection network for polyphonic Sound Event Detection","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2723513260","doi":"https://doi.org/10.1109/icassp.2017.7952259","mag":"2723513260"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"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/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), 201 Broadway, Cambridge, MA 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), 201 Broadway, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"766","last_page":"770"},"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":0.9994000196456909,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8249484300613403},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8149566650390625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6395610570907593},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6151623725891113},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5331225991249084},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5194730162620544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5179170966148376},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5046452283859253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49208515882492065},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4837815463542938},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40903037786483765},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0711519718170166}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8249484300613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149566650390625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6395610570907593},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6151623725891113},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5331225991249084},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5194730162620544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5179170966148376},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5046452283859253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49208515882492065},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4837815463542938},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40903037786483765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0711519718170166},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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/icassp.2017.7952259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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":18,"referenced_works":["https://openalex.org/W80364729","https://openalex.org/W1650531274","https://openalex.org/W1846473900","https://openalex.org/W2034424181","https://openalex.org/W2076618452","https://openalex.org/W2106792148","https://openalex.org/W2123843894","https://openalex.org/W2293202270","https://openalex.org/W2331166300","https://openalex.org/W2341412280","https://openalex.org/W2407005679","https://openalex.org/W2408239454","https://openalex.org/W2622742434","https://openalex.org/W3147849904","https://openalex.org/W6636898527","https://openalex.org/W6697171384","https://openalex.org/W6702387769","https://openalex.org/W6739564277"],"related_works":["https://openalex.org/W1542224353","https://openalex.org/W1661087619","https://openalex.org/W2053269318","https://openalex.org/W2116854923","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,15,22,28,34,95,100,141],"new":[4],"hybrid":[5,47],"approach":[6],"for":[7],"polyphonic":[8],"Sound":[9],"Event":[10],"Detection":[11],"(SED)":[12],"which":[13,86,183],"incorporates":[14],"temporal":[16,56],"structure":[17],"modeling":[18],"technique":[19],"based":[20,32],"on":[21,33,162,177],"hidden":[23],"Markov":[24],"model":[25,53],"(HMM)":[26],"with":[27,109,130],"frame-by-frame":[29,75],"detection":[30,63,103],"method":[31,129,146],"bidirectional":[35],"long":[36],"short-term":[37],"memory":[38],"(BLSTM)":[39],"recurrent":[40],"neural":[41],"network":[42,105],"(RNN).":[43],"The":[44],"proposed":[45,128,145],"BLSTM-HMM":[46],"system":[48],"makes":[49],"it":[50],"possible":[51],"to":[52,60,66,68,78,106,125],"sound":[54,84,101,111],"event-dependent":[55],"structures":[57],"and":[58,140,151,166],"also":[59,184],"perform":[61],"sequence-by-sequence":[62],"without":[64],"having":[65],"resort":[67],"thresholding":[69],"such":[70,134],"as":[71,135],"in":[72,190],"the":[73,119,148,163,178,186,191],"conventional":[74,132,149],"methods.":[76],"Furthermore,":[77],"effectively":[79],"reduce":[80],"insertion":[81],"errors":[82],"of":[83,159,169,174,182],"events,":[85],"often":[87],"occurs":[88],"under":[89],"noisy":[90],"conditions,":[91],"we":[92],"additionally":[93],"implement":[94],"binary":[96],"mask":[97],"post-processing":[98],"using":[99,118],"activity":[102],"(SAD)":[104],"identify":[107],"segments":[108],"any":[110],"event":[112],"activity.":[113],"We":[114],"conduct":[115],"an":[116,153,167],"experiment":[117],"DCASE":[120,192],"2016":[121,193],"task":[122,194],"2":[123,195],"dataset":[124],"compare":[126],"our":[127],"typical":[131],"methods,":[133],"non-negative":[136],"matrix":[137],"factorization":[138],"(NMF)":[139],"standard":[142],"BLSTM-RNN.":[143],"Our":[144],"outperforms":[147,185],"methods":[150],"achieves":[152],"F1-score":[154,168],"74.9":[155],"%":[156,171],"(error":[157,172],"rate":[158,173],"44.7":[160],"%)":[161,176],"event-based":[164],"evaluation,":[165,180],"80.5":[170],"33.8":[175],"segment-based":[179],"most":[181],"best":[187],"reported":[188],"result":[189],"challenge.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}