{"id":"https://openalex.org/W1980636726","doi":"https://doi.org/10.1145/2393347.2396323","title":"Bilingual analysis of song lyrics and audio words","display_name":"Bilingual analysis of song lyrics and audio words","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W1980636726","doi":"https://doi.org/10.1145/2393347.2396323","mag":"1980636726"},"language":"en","primary_location":{"id":"doi:10.1145/2393347.2396323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2393347.2396323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011045620","display_name":"Chin\u2010Chia Michael Yeh","orcid":"https://orcid.org/0000-0002-9807-2963"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Chia Yeh","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072013307","display_name":"Yuan-Ching Teng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Ching Teng","raw_affiliation_strings":["Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation, Academia Sinica, Taipei, Taiwan Roc","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"832"},"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":0.9973000288009644,"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/lyrics","display_name":"Lyrics","score":0.8288204669952393},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8065376281738281},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7108802199363708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6620950698852539},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6435868144035339},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5221317410469055},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5208097696304321},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4692870080471039},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.45531025528907776},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44663023948669434},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.432101309299469},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4180663824081421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40456005930900574},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3856620490550995},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23783981800079346},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1680559515953064},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09829255938529968}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8288204669952393},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8065376281738281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7108802199363708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6620950698852539},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6435868144035339},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5221317410469055},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5208097696304321},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4692870080471039},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.45531025528907776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44663023948669434},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.432101309299469},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4180663824081421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40456005930900574},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3856620490550995},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23783981800079346},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1680559515953064},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09829255938529968},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2393347.2396323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2393347.2396323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W103423544","https://openalex.org/W625810977","https://openalex.org/W1501755821","https://openalex.org/W1880262756","https://openalex.org/W1915070853","https://openalex.org/W1980599288","https://openalex.org/W2005876975","https://openalex.org/W2038678505","https://openalex.org/W2055356414","https://openalex.org/W2063978378","https://openalex.org/W2069959554","https://openalex.org/W2116373735","https://openalex.org/W2127566601","https://openalex.org/W2128064068","https://openalex.org/W2133824856","https://openalex.org/W2138635707","https://openalex.org/W2151103935","https://openalex.org/W2164480306","https://openalex.org/W2293869575","https://openalex.org/W2408751413","https://openalex.org/W2486605727","https://openalex.org/W2911964244","https://openalex.org/W6696794890"],"related_works":["https://openalex.org/W1481643945","https://openalex.org/W2994064478","https://openalex.org/W2144707026","https://openalex.org/W2153275212","https://openalex.org/W112239495","https://openalex.org/W2542820473","https://openalex.org/W2515398186","https://openalex.org/W2130068930","https://openalex.org/W2012665501","https://openalex.org/W2402674073"],"abstract_inverted_index":{"Thanks":[0],"to":[1,35,95,108,120],"the":[2,37,45,48,68,82,97],"development":[3],"of":[4,24,31,41,52,73,78,99],"music":[5,42,54,74],"audio":[6,86,114,129],"analysis,":[7],"state-of-the-art":[8],"techniques":[9],"can":[10],"now":[11],"detect":[12],"musical":[13],"attributes":[14],"such":[15],"as":[16],"timbre,":[17],"rhythm,":[18],"and":[19,26,47,70,85,103,113],"pitch":[20],"with":[21],"certain":[22],"level":[23],"reliability":[25],"effectiveness.":[27],"An":[28],"emerging":[29],"body":[30],"research":[32],"has":[33],"begun":[34],"model":[36],"high-level":[38],"perceptual":[39],"properties":[40],"listening,":[43],"including":[44],"mood":[46,125],"preferable":[49],"listening":[50],"context":[51],"a":[53,61,76],"piece.":[55],"Towards":[56],"this":[57],"goal,":[58],"we":[59,90],"propose":[60],"novel":[62],"text-like":[63,117],"feature":[64,101],"representation":[65,118],"that":[66],"encodes":[67],"rich":[69],"time-varying":[71],"information":[72],"using":[75],"composite":[77],"features":[79],"extracted":[80],"from":[81],"song":[83],"lyrics":[84],"signals.":[87],"In":[88],"particular,":[89],"investigate":[91],"dictionary":[92],"learning":[93],"algorithms":[94],"optimize":[96],"generation":[98],"local":[100],"descriptors":[102],"also":[104],"probabilistic":[105],"topic":[106],"models":[107],"group":[109],"semantically":[110],"relevant":[111],"text":[112],"words.":[115],"This":[116],"leads":[119],"significant":[121],"improvement":[122],"in":[123],"automatic":[124],"classification":[126],"over":[127],"conventional":[128],"features.":[130]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
