{"id":"https://openalex.org/W2034302001","doi":"https://doi.org/10.1145/2578726.2578802","title":"A Robust Audio Similarity Estimation Method for Audio Alignment in Mobile Karaoke Apps","display_name":"A Robust Audio Similarity Estimation Method for Audio Alignment in Mobile Karaoke Apps","publication_year":2014,"publication_date":"2014-04-01","ids":{"openalex":"https://openalex.org/W2034302001","doi":"https://doi.org/10.1145/2578726.2578802","mag":"2034302001"},"language":"en","primary_location":{"id":"doi:10.1145/2578726.2578802","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2578726.2578802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of International Conference on Multimedia Retrieval","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/A5068584688","display_name":"Jinghui Mo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinghui Mo","raw_affiliation_strings":["ICST, Peking University"],"affiliations":[{"raw_affiliation_string":"ICST, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102220317","display_name":"Yansong Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Feng","raw_affiliation_strings":["ICST, Peking University"],"affiliations":[{"raw_affiliation_string":"ICST, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037132097","display_name":"Dongyan Zhao","orcid":"https://orcid.org/0000-0002-0396-6703"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyan Zhao","raw_affiliation_strings":["ICST, Peking University"],"affiliations":[{"raw_affiliation_string":"ICST, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068584688"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10486111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"495","last_page":"498"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919000267982483,"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":0.7694447040557861},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7448595762252808},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7348085641860962},{"id":"https://openalex.org/keywords/android","display_name":"Android (operating system)","score":0.7012165784835815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38931548595428467},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32290035486221313},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11975401639938354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694447040557861},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7448595762252808},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7348085641860962},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.7012165784835815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38931548595428467},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32290035486221313},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11975401639938354},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2578726.2578802","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2578726.2578802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W48943499","https://openalex.org/W67806156","https://openalex.org/W205731033","https://openalex.org/W313810197","https://openalex.org/W1480825190","https://openalex.org/W1971703391","https://openalex.org/W2029600726","https://openalex.org/W2126410803","https://openalex.org/W2142927150","https://openalex.org/W6608325550","https://openalex.org/W6681102793"],"related_works":["https://openalex.org/W2355862304","https://openalex.org/W2347883734","https://openalex.org/W2356108042","https://openalex.org/W2030250808","https://openalex.org/W2376796979","https://openalex.org/W2382147347","https://openalex.org/W4313577291","https://openalex.org/W2185797214","https://openalex.org/W4285069890","https://openalex.org/W2143082658"],"abstract_inverted_index":{"With":[0],"smartphones":[1],"further":[2],"integrating":[3],"into":[4],"our":[5,105],"lives,":[6],"more":[7],"people":[8],"start":[9],"to":[10,19,46,69,97],"sing":[11],"using":[12],"mobile":[13],"karaoke":[14,42],"apps":[15],"instead":[16],"of":[17,29],"going":[18],"a":[20,88],"KTV":[21],"club.":[22],"However,":[23],"the":[24,48,52,71,108],"playback":[25],"and":[26,51,77,114,119],"record":[27,49],"APIs":[28],"Android":[30,41],"systems":[31],"do":[32],"not":[33],"respond":[34],"in":[35,111],"real-time":[36],"when":[37,55],"called.":[38],"Thus,":[39],"an":[40],"app":[43],"will":[44],"have":[45],"align":[47],"music":[50],"original":[53],"accompaniment":[54],"super-posing":[56],"those":[57],"two":[58,75],"audios.":[59],"Dynamic":[60],"time":[61],"warping":[62],"(DTW)":[63],"based":[64],"algorithms":[65],"are":[66],"usually":[67],"used":[68],"find":[70],"optimal":[72],"alignment":[73],"between":[74],"audios":[76],"yield":[78],"best":[79],"result":[80],"so":[81],"far.":[82],"In":[83],"this":[84,99],"paper,":[85],"we":[86],"propose":[87],"simple":[89],"yet":[90],"robust":[91],"approach":[92],"by":[93],"considering":[94],"waveform":[95],"similarities":[96],"solve":[98],"problem.":[100],"Experimental":[101],"results":[102],"show":[103],"that":[104],"method":[106,110],"outperforms":[107],"state-of-the-art":[109],"both":[112],"accuracy":[113],"robustness":[115],"across":[116],"different":[117],"genres":[118],"devices.":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
