{"id":"https://openalex.org/W1666743510","doi":"https://doi.org/10.1109/icpr.2002.1048204","title":"A robust audio searching method for cellular-phone-based music information retrieval","display_name":"A robust audio searching method for cellular-phone-based music information retrieval","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W1666743510","doi":"https://doi.org/10.1109/icpr.2002.1048204","mag":"1666743510"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2002.1048204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2002.1048204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Object recognition supported by user interaction for service robots","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/A5110501585","display_name":"Takayuki Kurozumi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"T. Kurozumi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan","NTT Communication Science Laboratories NTT Corporation Atsugi Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories NTT Corporation Atsugi Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. Kashino","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan","NTT Communication Science Laboratories NTT Corporation Atsugi Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories NTT Corporation Atsugi Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085309296","display_name":"Hiroshi Murase","orcid":"https://orcid.org/0000-0002-8103-9294"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H. Murase","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan","NTT Communication Science Laboratories NTT Corporation Atsugi Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories NTT Corporation Atsugi Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110501585"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5856,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65485791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"991","last_page":"994"},"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":0.9998000264167786,"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/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":0.7918151021003723},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6153941750526428},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5711708068847656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5668085217475891},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47102174162864685},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4675053060054779},{"id":"https://openalex.org/keywords/signal-subspace","display_name":"Signal subspace","score":0.4590339660644531},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4364608824253082},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4149259328842163},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41405871510505676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3677877187728882},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3413219749927521},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31472480297088623},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18232327699661255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918151021003723},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6153941750526428},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5711708068847656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5668085217475891},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47102174162864685},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4675053060054779},{"id":"https://openalex.org/C2777121530","wikidata":"https://www.wikidata.org/wiki/Q7512739","display_name":"Signal subspace","level":4,"score":0.4590339660644531},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4364608824253082},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4149259328842163},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41405871510505676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3677877187728882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3413219749927521},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31472480297088623},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18232327699661255},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2002.1048204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2002.1048204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Object recognition supported by user interaction for service robots","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1752337664","https://openalex.org/W2069976350","https://openalex.org/W2128653836","https://openalex.org/W2138011093","https://openalex.org/W6637707565"],"related_works":["https://openalex.org/W2379264914","https://openalex.org/W2153912708","https://openalex.org/W2118094278","https://openalex.org/W2639400695","https://openalex.org/W3126343058","https://openalex.org/W2949173582","https://openalex.org/W2089410207","https://openalex.org/W4300048032","https://openalex.org/W2367577754","https://openalex.org/W2387532542"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,7,25,30],"search":[3,44],"method":[4,64,113],"for":[5],"detecting":[6],"query":[8,17,51],"audio":[9,14],"signal":[10,18],"fragment":[11],"in":[12,33,40,106],"long":[13],"recordings.":[15],"The":[16,63,74],"is":[19,45,76,114],"assumed":[20],"to":[21,57,78,82,91],"be":[22],"captured":[23],"by":[24],"portable":[26],"terminal,":[27],"such":[28],"as":[29],"cellular":[31,104],"phone,":[32],"the":[34,47,50,89,97,107,111],"real":[35,108],"world.":[36],"A":[37],"major":[38],"problem":[39],"this":[41],"kind":[42],"of":[43,49,99],"that":[46,95],"features":[48,80],"sound":[52],"may":[53],"include":[54],"distortions":[55],"due":[56],"terminal":[58],"characteristics":[59],"or":[60],"environment":[61],"noise.":[62],"proposed":[65,112],"comprises":[66],"local":[67],"time-frequency-region":[68],"normalization":[69],"and":[70,85,88],"robust":[71],"subspace":[72],"spanning.":[73],"former":[75],"used":[77],"make":[79],"invariant":[81],"additive":[83],"noise":[84],"frequency":[86,93],"characteristics,":[87],"latter":[90],"choose":[92],"bands":[94],"minimize":[96],"effect":[98],"feature":[100],"distortions.":[101],"Experiments":[102],"using":[103],"phones":[105],"world":[109],"show":[110],"effective.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
