{"id":"https://openalex.org/W2765200746","doi":"https://doi.org/10.1109/icassp.2018.8461524","title":"Content-Based Representations of Audio Using Siamese Neural Networks","display_name":"Content-Based Representations of Audio Using Siamese Neural Networks","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2765200746","doi":"https://doi.org/10.1109/icassp.2018.8461524","mag":"2765200746"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.10974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075510192","display_name":"Pranay Manocha","orcid":"https://orcid.org/0000-0003-3284-5908"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranay Manocha","raw_affiliation_strings":["Department of Electronics and Electrical Engineering IIT Guwahati, India","[Department of Electronics and Electrical Engineering IIT Guwahati, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering IIT Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]},{"raw_affiliation_string":"[Department of Electronics and Electrical Engineering IIT Guwahati, India]","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058296176","display_name":"Rohan Badlani","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohan Badlani","raw_affiliation_strings":["Department of Computer Science, India","Department of Computer Science, BITS, Pilani, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, India","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, BITS, Pilani, India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101531439","display_name":"Ankit Shah","orcid":"https://orcid.org/0000-0002-8838-5421"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankit Shah","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073250019","display_name":"Benjamin Elizalde","orcid":"https://orcid.org/0000-0001-6461-5790"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Elizalde","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Language Technologies Institute, Carnegie Mellon University, Pittsburgh, United States]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1804,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.29755034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3136","last_page":"3140"},"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":0.9973999857902527,"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":0.9930999875068665,"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":0.7769511938095093},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6371456384658813},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5597516298294067},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5467405319213867},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5275530219078064},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4993741512298584},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4875478148460388},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.484406054019928},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.48269009590148926},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4659811854362488},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.45543843507766724},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43816015124320984},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4262462556362152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3705672025680542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3626510798931122},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2793160080909729},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2627101540565491},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.12381115555763245},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.090675950050354},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06693094968795776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7769511938095093},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6371456384658813},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5597516298294067},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5467405319213867},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5275530219078064},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4993741512298584},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4875478148460388},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.484406054019928},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.48269009590148926},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4659811854362488},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.45543843507766724},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43816015124320984},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4262462556362152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3705672025680542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3626510798931122},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2793160080909729},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2627101540565491},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.12381115555763245},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.090675950050354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06693094968795776},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.10974","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.10974","pdf_url":"https://arxiv.org/pdf/1710.10974","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2765200746","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1710.10974","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1710.10974","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1710.10974","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.10974","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.10974","pdf_url":"https://arxiv.org/pdf/1710.10974","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2765200746.pdf","grobid_xml":"https://content.openalex.org/works/W2765200746.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W219040644","https://openalex.org/W2010486494","https://openalex.org/W2038484192","https://openalex.org/W2038678505","https://openalex.org/W2047484428","https://openalex.org/W2074188409","https://openalex.org/W2086384421","https://openalex.org/W2099797668","https://openalex.org/W2103861099","https://openalex.org/W2109244020","https://openalex.org/W2127589108","https://openalex.org/W2145568986","https://openalex.org/W2147069236","https://openalex.org/W2401100696","https://openalex.org/W2511925527","https://openalex.org/W2516890051","https://openalex.org/W2566935005","https://openalex.org/W2579700650","https://openalex.org/W2717715803","https://openalex.org/W2953259386","https://openalex.org/W2963389687","https://openalex.org/W3021908862","https://openalex.org/W6603388714","https://openalex.org/W6604987197","https://openalex.org/W6643326691","https://openalex.org/W6660313906","https://openalex.org/W6675120338","https://openalex.org/W6675755862","https://openalex.org/W6680272447","https://openalex.org/W6682556939","https://openalex.org/W6712990459","https://openalex.org/W6714029020","https://openalex.org/W6725015247"],"related_works":["https://openalex.org/W2964287480","https://openalex.org/W1486372608","https://openalex.org/W2369488382","https://openalex.org/W1529773983","https://openalex.org/W2157933833","https://openalex.org/W1576578512","https://openalex.org/W2165730290","https://openalex.org/W2765345004","https://openalex.org/W2793660815","https://openalex.org/W2565045365","https://openalex.org/W2023934785","https://openalex.org/W2097068947","https://openalex.org/W2116225897","https://openalex.org/W2072938301","https://openalex.org/W2150322163","https://openalex.org/W2162499636","https://openalex.org/W2157754032","https://openalex.org/W3015061299","https://openalex.org/W2087570585","https://openalex.org/W2756750649"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,112],"focus":[4],"on":[5,105],"the":[6,33,54,64,86],"problem":[7,29,34],"of":[8,35,39,93],"content-based":[9],"retrieval":[10,92],"for":[11,22,82,122],"audio,":[12,40],"which":[13,41,50,62],"aims":[14,42],"to":[15,32,43,53,77,85],"retrieve":[16,44],"all":[17],"semantically":[18,94],"similar":[19,31,52,81,95,125],"audio":[20,25,65,88,127],"recordings":[21,124],"a":[23,48,59,67],"given":[24],"clip":[26],"query.":[27],"This":[28],"is":[30,76],"query":[36],"by":[37],"example":[38],"media":[45],"samples":[46],"from":[47],"database,":[49],"are":[51],"user-provided":[55],"example.":[56],"We":[57],"propose":[58],"novel":[60],"approach":[61],"encodes":[63],"into":[66],"vector":[68],"representation":[69],"using":[70],"Siamese":[71],"Neural":[72],"Networks.":[73],"The":[74],"goal":[75],"obtain":[78],"an":[79],"encoding":[80],"files":[83],"belonging":[84],"same":[87],"class,":[89],"thus":[90],"allowing":[91],"audio.":[96],"Using":[97],"simple":[98,106],"similarity":[99,111],"measures":[100],"such":[101],"as":[102],"those":[103],"based":[104],"euclidean":[107],"distance":[108],"and":[109],"cosine":[110],"show":[113],"that":[114],"these":[115],"representations":[116],"can":[117],"be":[118],"very":[119],"effectively":[120],"used":[121],"retrieving":[123],"in":[126],"content.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}