{"id":"https://openalex.org/W2775430159","doi":"https://doi.org/10.1109/waspaa.2017.8170044","title":"IMINET: Convolutional semi-siamese networks for sound search by vocal imitation","display_name":"IMINET: Convolutional semi-siamese networks for sound search by vocal imitation","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2775430159","doi":"https://doi.org/10.1109/waspaa.2017.8170044","mag":"2775430159"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8170044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5100444198","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0003-0465-6341"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100444198"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":2.0342,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88484096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1001","issue":null,"first_page":"304","last_page":"308"},"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":0.9994999766349792,"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":0.9988999962806702,"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/imitation","display_name":"Imitation","score":0.7604267597198486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269744873046875},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6956993341445923},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6639979481697083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6294454336166382},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6037972569465637},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5265213251113892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44740888476371765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3439866304397583},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07510784268379211}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7604267597198486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269744873046875},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6956993341445923},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6639979481697083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6294454336166382},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6037972569465637},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5265213251113892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44740888476371765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3439866304397583},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07510784268379211},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa.2017.8170044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W604354567","https://openalex.org/W1522301498","https://openalex.org/W1532076566","https://openalex.org/W1606357646","https://openalex.org/W1929856797","https://openalex.org/W1965447465","https://openalex.org/W1965555277","https://openalex.org/W1988566301","https://openalex.org/W2000420612","https://openalex.org/W2008066450","https://openalex.org/W2027518030","https://openalex.org/W2099797668","https://openalex.org/W2100495367","https://openalex.org/W2100805904","https://openalex.org/W2103219113","https://openalex.org/W2127589108","https://openalex.org/W2128160875","https://openalex.org/W2130325614","https://openalex.org/W2138286601","https://openalex.org/W2146229144","https://openalex.org/W2157364932","https://openalex.org/W2167700723","https://openalex.org/W2406791552","https://openalex.org/W2470394683","https://openalex.org/W2517544051","https://openalex.org/W2964121744","https://openalex.org/W3091905774","https://openalex.org/W4250596551","https://openalex.org/W6618552045","https://openalex.org/W6631190155","https://openalex.org/W6631814781","https://openalex.org/W6636400922","https://openalex.org/W6640083356","https://openalex.org/W6675120338","https://openalex.org/W6783596713","https://openalex.org/W6913044885"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4387104524"],"abstract_inverted_index":{"Searching":[0],"sounds":[1],"by":[2,31,91],"text":[3,9],"labels":[4,10],"is":[5],"often":[6],"difficult,":[7],"as":[8,118],"cannot":[11],"always":[12],"provide":[13],"sufficient":[14],"information":[15],"for":[16,28],"the":[17,75,89,98,107,126,130,134,147],"sound":[18,29,63,81],"content.":[19],"Previously":[20],"we":[21,37],"proposed":[22],"an":[23],"unsupervised":[24],"system":[25],"called":[26,45],"IMISOUND":[27,117,131,148],"search":[30],"vocal":[32,60,78],"imitation.":[33],"In":[34],"this":[35],"paper,":[36],"further":[38],"propose":[39,84,103],"a":[40,69,119],"Convolutional":[41,52],"Semi-Siamese":[42],"Network":[43],"(CSN)":[44],"IMINET.":[46],"IMINET":[47,145],"uses":[48],"two":[49,99],"towers":[50],"of":[51,88,106,110,116,125,136],"Neural":[53],"Networks":[54],"(CNN)":[55],"to":[56,73,133,141],"extract":[57],"features":[58],"from":[59,129],"imitations":[61,79],"and":[62,80,114,140,146],"recordings,":[64],"respectively.":[65],"It":[66],"then":[67],"adopts":[68],"fully":[70],"connected":[71],"network":[72],"predict":[74],"similarity":[76],"between":[77,97,144],"recordings.":[82],"We":[83,101],"three":[85],"different":[86,93,112,138,142],"configurations":[87,113],"CSN":[90],"choosing":[92],"weight":[94],"sharing":[95],"strategies":[96],"towers.":[100],"also":[102],"late":[104],"fusion":[105,135],"retrieval":[108,127],"results":[109],"IMINET's":[111,137],"those":[115],"baseline.":[120,149],"Experiments":[121],"show":[122],"significant":[123],"improvements":[124],"performance":[128],"baseline":[132],"configurations,":[139],"fusions":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}