{"id":"https://openalex.org/W3213830065","doi":"https://doi.org/10.1109/mlsp52302.2021.9596435","title":"SiamNet: Siamese CNN Based Similarity Model for Adversarially Generated Environmental Sounds","display_name":"SiamNet: Siamese CNN Based Similarity Model for Adversarially Generated Environmental Sounds","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3213830065","doi":"https://doi.org/10.1109/mlsp52302.2021.9596435","mag":"3213830065"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5027364983","display_name":"Aswathy Madhu","orcid":"https://orcid.org/0000-0002-6392-3318"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aswathy Madhu","raw_affiliation_strings":["College of Engineering, Trivandrum","Govt. Engineering College, Barton Hill, Thiruvananthapuram"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Trivandrum","institution_ids":[]},{"raw_affiliation_string":"Govt. Engineering College, Barton Hill, Thiruvananthapuram","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113471027","display_name":"K. Suresh","orcid":null},"institutions":[{"id":"https://openalex.org/I3129367976","display_name":"A P J Abdul Kalam Technological University","ror":"https://ror.org/04yn30r61","country_code":"IN","type":"education","lineage":["https://openalex.org/I3129367976"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suresh K","raw_affiliation_strings":["Affiliated to APJ Abdul Kalam Technological University, Kerala, India","Govt. Engineering College, Barton Hill, Thiruvananthapuram"],"affiliations":[{"raw_affiliation_string":"Affiliated to APJ Abdul Kalam Technological University, Kerala, India","institution_ids":["https://openalex.org/I3129367976"]},{"raw_affiliation_string":"Govt. Engineering College, Barton Hill, Thiruvananthapuram","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027364983"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.15341447,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"6","issue":null,"first_page":"1","last_page":"6"},"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":0.9972000122070312,"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":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.8007218837738037},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7445318698883057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6373143196105957},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.536338746547699},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5359595417976379},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5185616612434387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4645765721797943},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44513049721717834},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4421824514865875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3774452209472656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34322088956832886},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24667632579803467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007218837738037},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7445318698883057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373143196105957},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.536338746547699},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5359595417976379},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5185616612434387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4645765721797943},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44513049721717834},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4421824514865875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3774452209472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34322088956832886},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24667632579803467},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.550000011920929,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W2033875152","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2099471712","https://openalex.org/W2100071400","https://openalex.org/W2108708552","https://openalex.org/W2127589108","https://openalex.org/W2191779130","https://openalex.org/W2552611751","https://openalex.org/W2566832195","https://openalex.org/W2583180462","https://openalex.org/W2749617271","https://openalex.org/W2771254707","https://openalex.org/W2890913619","https://openalex.org/W2894295011","https://openalex.org/W2963373786","https://openalex.org/W2963709863","https://openalex.org/W2963865839","https://openalex.org/W2963876058","https://openalex.org/W2963981733","https://openalex.org/W2964267196","https://openalex.org/W2988491440","https://openalex.org/W3091905774","https://openalex.org/W3097934054","https://openalex.org/W3201409833","https://openalex.org/W4297817572","https://openalex.org/W4320013936","https://openalex.org/W6631943919","https://openalex.org/W6675172270","https://openalex.org/W6718379498","https://openalex.org/W6729939709","https://openalex.org/W6732940373","https://openalex.org/W6733322467","https://openalex.org/W6743994364","https://openalex.org/W6755257315","https://openalex.org/W6765779288","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Recently,":[0],"Generative":[1],"Adversarial":[2],"Networks":[3],"(GANs)":[4],"are":[5,34,45,69,157],"being":[6],"used":[7],"extensively":[8],"in":[9],"machine":[10],"learning":[11],"applications":[12],"for":[13,24,48,67],"synthetic":[14,107],"generation":[15,74],"of":[16,27,30,40,58,75,106,134,154],"image":[17],"and":[18,71,99,122,180],"audio":[19,68,78,108,182],"samples.":[20,124,183],"However":[21],"efficient":[22],"methods":[23],"the":[25,28,41,73,104,116,120,143,155,164,174,178],"evaluation":[26,43],"quality":[29,105],"GAN":[31,80],"generated":[32,109,123,146,179],"samples":[33],"not":[35,52],"available":[36],"yet.":[37],"Moreover,":[38],"most":[39],"existing":[42],"metrics":[44,64],"developed":[46,65],"exclusively":[47],"images":[49],"which":[50,94],"may":[51],"work":[53],"well":[54],"with":[55,160],"other":[56],"types":[57],"data":[59],"such":[60],"as":[61],"audio.":[62],"Evaluation":[63],"specifically":[66],"rare":[70],"hence":[72],"perceptually":[76],"acceptable":[77],"using":[79,147],"is":[81,128,140],"difficult.":[82],"In":[83],"this":[84,88],"work,":[85],"we":[86],"address":[87],"problem.":[89],"We":[90],"propose":[91],"Siamese":[92],"CNN":[93],"simultaneously":[95],"learns":[96],"feature":[97],"representation":[98],"similarity":[100,126,152,176],"measure":[101],"to":[102],"evaluate":[103],"by":[110],"GAN.":[111,148],"The":[112,137,149],"proposed":[113],"method":[114],"estimates":[115],"perceptual":[117,175],"proximity":[118],"between":[119,177],"original":[121,181],"Our":[125],"model":[127,139,171],"trained":[129],"on":[130,142],"two":[131],"standard":[132],"datasets":[133],"environmental":[135,144],"sounds.":[136],"pre-trained":[138],"evaluated":[141],"sounds":[145],"predicted":[150],"mean":[151],"score":[153],"SiamNet":[156],"highly":[158],"correlated":[159],"human":[161],"ratings":[162],"at":[163],"class":[165],"level.":[166],"This":[167],"indicates":[168],"that":[169],"our":[170],"successfully":[172],"captures":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}