{"id":"https://openalex.org/W3205514615","doi":"https://doi.org/10.1145/3478384.3478423","title":"Similarity Analysis of Visual Sketch-based Search for Sounds","display_name":"Similarity Analysis of Visual Sketch-based Search for Sounds","publication_year":2021,"publication_date":"2021-09-01","ids":{"openalex":"https://openalex.org/W3205514615","doi":"https://doi.org/10.1145/3478384.3478423","mag":"3205514615"},"language":"en","primary_location":{"id":"doi:10.1145/3478384.3478423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3478384.3478423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2021","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/A5021718052","display_name":"Lars Engeln","orcid":"https://orcid.org/0000-0002-9268-4854"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars Engeln","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076447972","display_name":"Nhat Long Le","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nhat Long Le","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040207023","display_name":"Matthew McGinity","orcid":"https://orcid.org/0000-0002-8923-6284"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthew McGinity","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056517923","display_name":"Rainer Groh","orcid":"https://orcid.org/0000-0001-5031-7493"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Groh","raw_affiliation_strings":["Technische Universit\u00e4t Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3088,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.55613577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8150901794433594},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6318030953407288},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5412494540214539},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5285854339599609},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5271220803260803},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.5059868693351746},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4974386990070343},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.49108123779296875},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4713670015335083},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4711945056915283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4609639346599579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4315975308418274},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4273138642311096},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41975271701812744},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35200467705726624},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11215919256210327},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09982937574386597},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09596127271652222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150901794433594},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6318030953407288},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5412494540214539},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5285854339599609},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5271220803260803},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.5059868693351746},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4974386990070343},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.49108123779296875},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4713670015335083},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4711945056915283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4609639346599579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4315975308418274},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4273138642311096},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41975271701812744},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35200467705726624},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11215919256210327},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09982937574386597},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09596127271652222},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3478384.3478423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3478384.3478423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1594474154","https://openalex.org/W1964073652","https://openalex.org/W1966280390","https://openalex.org/W1967815732","https://openalex.org/W1970214393","https://openalex.org/W2003941100","https://openalex.org/W2069416551","https://openalex.org/W2093192785","https://openalex.org/W2101900719","https://openalex.org/W2137838732","https://openalex.org/W2161676851","https://openalex.org/W2162200825","https://openalex.org/W2183543165","https://openalex.org/W2295581252","https://openalex.org/W2340600463","https://openalex.org/W2397271393","https://openalex.org/W2417584481","https://openalex.org/W2418353079","https://openalex.org/W2493235950","https://openalex.org/W2526050071","https://openalex.org/W2561826558","https://openalex.org/W2579752503","https://openalex.org/W2606712314","https://openalex.org/W2768267620","https://openalex.org/W2795389793","https://openalex.org/W2795662094","https://openalex.org/W2897411159","https://openalex.org/W2906259846","https://openalex.org/W2948475314","https://openalex.org/W2963435138","https://openalex.org/W2973909019","https://openalex.org/W2986592617","https://openalex.org/W2997351497","https://openalex.org/W3004250220","https://openalex.org/W3010914815","https://openalex.org/W3041053424","https://openalex.org/W3104866538","https://openalex.org/W3180072716","https://openalex.org/W4234051837","https://openalex.org/W4251455824"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W3013693939"],"abstract_inverted_index":{"Searching":[0],"through":[1],"a":[2,7,12,63,73,93,104,133,143,167],"large":[3],"audio":[4,127,152],"database":[5],"for":[6,92,154,172],"specific":[8],"sound":[9,64],"can":[10],"be":[11,36],"slow":[13],"and":[14,123,139,165],"tedious":[15],"task":[16],"with":[17,62],"detrimental":[18],"effects":[19],"on":[20,80,149],"creative":[21],"workflow.":[22],"Listening":[23],"to":[24,42,65,77,103,163],"each":[25],"sample":[26],"is":[27,132],"time":[28],"consuming,":[29],"while":[30],"textual":[31],"descriptions":[32],"or":[33,39],"tags":[34],"may":[35],"insufficient,":[37],"unavailable":[38],"simply":[40],"unable":[41],"meaningfully":[43],"capturing":[44],"certain":[45],"sonic":[46,140],"qualities.":[47],"This":[48],"paper":[49],"explores":[50],"the":[51,58,67,101,125,155],"use":[52],"of":[53,95,107],"visual":[54,90,138,168],"sketches":[55,119],"that":[56],"express":[57],"mental":[59],"model":[60],"associated":[61,126],"accelerate":[66],"search":[68,156,170],"process.":[69],"To":[70],"achieve":[71],"this,":[72],"study":[74],"was":[75],"conducted":[76],"collect":[78],"data":[79,102],"how":[81],"30":[82,96],"people":[83],"visually":[84],"represent":[85],"sound,":[86],"by":[87],"providing":[88],"hand-sketched":[89],"representations":[91],"range":[94],"different":[97,111],"sounds.":[98,173],"After":[99],"augmenting":[100],"sparse":[105],"set":[106],"855":[108],"samples,":[109],"two":[110],"autoencoder":[112,135],"were":[113,160],"trained.":[114],"The":[115,129],"one":[116,131],"finds":[117],"similar":[118],"in":[120,142],"latent":[121],"space":[122,146],"delivers":[124],"files.":[128],"other":[130],"multimodal":[134],"combining":[136],"both":[137,159],"cues":[141],"common":[144],"feature":[145],"but":[147],"lacks":[148],"having":[150],"no":[151],"input":[153],"task.":[157],"These":[158],"then":[161],"used":[162],"implement":[164],"discuss":[166],"query-by-sketch":[169],"interface":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
