{"id":"https://openalex.org/W4224929689","doi":"https://doi.org/10.1109/icassp43922.2022.9747835","title":"Environmental Sound Extraction Using Onomatopoeic Words","display_name":"Environmental Sound Extraction Using Onomatopoeic Words","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224929689","doi":"https://doi.org/10.1109/icassp43922.2022.9747835"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747835","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5113959532","display_name":"Yuki Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Okamoto","raw_affiliation_strings":["Ritsumeikan University,Japan","Ritsumeikan University, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ritsumeikan University, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113821883","display_name":"Masaaki Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaaki Yamamoto","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009991655","display_name":"Keisuke Imoto","orcid":"https://orcid.org/0000-0002-0703-8293"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["Doshisha University,Japan","Doshisha University, Japan"],"affiliations":[{"raw_affiliation_string":"Doshisha University,Japan","institution_ids":["https://openalex.org/I133984924"]},{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052394367","display_name":"Yohei Kawaguchi","orcid":"https://orcid.org/0000-0002-2329-5441"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Kawaguchi","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113959532"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.8591,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72575039,"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":"221","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9969000220298767,"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":0.9891999959945679,"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/onomatopoeia","display_name":"Onomatopoeia","score":0.9520097374916077},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8867782354354858},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6681232452392578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6510065197944641},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5821753740310669},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5667989253997803},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5491464734077454},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5104728937149048},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4038871228694916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3360222578048706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20994144678115845},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18238171935081482},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07746264338493347}],"concepts":[{"id":"https://openalex.org/C22432085","wikidata":"https://www.wikidata.org/wiki/Q170239","display_name":"Onomatopoeia","level":2,"score":0.9520097374916077},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8867782354354858},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6681232452392578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6510065197944641},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5821753740310669},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5667989253997803},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5491464734077454},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5104728937149048},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4038871228694916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3360222578048706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20994144678115845},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18238171935081482},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07746264338493347},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747835","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310366","display_name":"Hitachi","ror":"https://ror.org/02exqgm79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W20241248","https://openalex.org/W1901129140","https://openalex.org/W2021036184","https://openalex.org/W2058341666","https://openalex.org/W2120847449","https://openalex.org/W2127851351","https://openalex.org/W2406791552","https://openalex.org/W2774707525","https://openalex.org/W2801393360","https://openalex.org/W2890913619","https://openalex.org/W2898963093","https://openalex.org/W2940168379","https://openalex.org/W2952218014","https://openalex.org/W2968917279","https://openalex.org/W2969034647","https://openalex.org/W2998657200","https://openalex.org/W3003322464","https://openalex.org/W3004910802","https://openalex.org/W3012058607","https://openalex.org/W3095263845","https://openalex.org/W3099330747","https://openalex.org/W6600817012","https://openalex.org/W6639824700","https://openalex.org/W6746914816","https://openalex.org/W6766938422","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W2315379384","https://openalex.org/W3197205159","https://openalex.org/W2313695185","https://openalex.org/W4280511947","https://openalex.org/W2767010592","https://openalex.org/W2369458119","https://openalex.org/W2327292841","https://openalex.org/W2993672003","https://openalex.org/W2560876968","https://openalex.org/W4372258428"],"abstract_inverted_index":{"An":[0],"onomatopoeic":[1,32,57,89],"word,":[2],"which":[3],"is":[4,13],"a":[5,11,47,60],"character":[6],"sequence":[7],"that":[8,76,97],"phonetically":[9],"imitates":[10],"sound,":[12],"effective":[14],"in":[15],"expressing":[16],"characteristics":[17],"of":[18],"sound":[19,38,68,85],"such":[20],"as":[21],"duration,":[22],"pitch,":[23],"and":[24,55,91],"timbre.":[25],"We":[26],"propose":[27],"an":[28,51,56],"environmental-sound-extraction":[29],"method":[30,79],"using":[31,59],"words":[33],"to":[34,39,87,101],"specify":[35,102],"the":[36,65,71,77,83,88,103],"target":[37,67,84,104],"be":[40],"extracted.":[41],"By":[42],"this":[43],"method,":[44],"we":[45],"estimate":[46],"time-frequency":[48],"mask":[49],"from":[50],"input":[52],"mixture":[53],"spectrogram":[54],"word":[58,90],"U-Net":[61],"architecture,":[62],"then":[63],"extract":[64,81],"corresponding":[66,86],"by":[69],"masking":[70],"spectrogram.":[72],"Experimental":[73],"results":[74],"indicate":[75],"proposed":[78],"can":[80],"only":[82],"performs":[92],"better":[93],"than":[94],"conventional":[95],"methods":[96],"use":[98],"sound-event":[99],"classes":[100],"sound.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}