{"id":"https://openalex.org/W4372267973","doi":"https://doi.org/10.1109/icassp49357.2023.10095926","title":"Textless Speech-to-Music Retrieval Using Emotion Similarity","display_name":"Textless Speech-to-Music Retrieval Using Emotion Similarity","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267973","doi":"https://doi.org/10.1109/icassp49357.2023.10095926"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5010952526","display_name":"SeungHeon Doh","orcid":"https://orcid.org/0000-0002-8448-9928"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"SeungHeon Doh","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,South Korea","Graduate School of Culture Technology, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041096205","display_name":"Minz Won","orcid":"https://orcid.org/0000-0002-6921-1733"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minz Won","raw_affiliation_strings":["ByteDance,USA","ByteDance, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,USA","institution_ids":[]},{"raw_affiliation_string":"ByteDance, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011038627","display_name":"Keunwoo Choi","orcid":"https://orcid.org/0000-0002-5305-5342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keunwoo Choi","raw_affiliation_strings":["Gaudio Lab,South Korea","Gaudio Lab, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaudio Lab,South Korea","institution_ids":[]},{"raw_affiliation_string":"Gaudio Lab, South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,South Korea","Graduate School of Culture Technology, KAIST, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9957000017166138,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.6649946570396423},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5948339700698853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5876877903938293},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5870801210403442},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5790610313415527},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4890523850917816},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4205591678619385},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41865259408950806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40192046761512756},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3600727617740631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35761046409606934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10547047853469849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6649946570396423},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5948339700698853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5876877903938293},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5870801210403442},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5790610313415527},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4890523850917816},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4205591678619385},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41865259408950806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40192046761512756},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3600727617740631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35761046409606934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10547047853469849},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2069870183","https://openalex.org/W2146334809","https://openalex.org/W2250539671","https://openalex.org/W2476034201","https://openalex.org/W2593116425","https://openalex.org/W2604959036","https://openalex.org/W2765440071","https://openalex.org/W2786672974","https://openalex.org/W2798357113","https://openalex.org/W2803193013","https://openalex.org/W2962970472","https://openalex.org/W2963389687","https://openalex.org/W2978017171","https://openalex.org/W2990387939","https://openalex.org/W3036601975","https://openalex.org/W3128376221","https://openalex.org/W3180663620","https://openalex.org/W3197642003","https://openalex.org/W3198528147","https://openalex.org/W3206192140","https://openalex.org/W3214872027","https://openalex.org/W4226027884","https://openalex.org/W4281945262","https://openalex.org/W4286850225","https://openalex.org/W4312120828","https://openalex.org/W4312319752","https://openalex.org/W6721087566","https://openalex.org/W6736327223","https://openalex.org/W6748816842","https://openalex.org/W6768851824","https://openalex.org/W6771024394","https://openalex.org/W6780218876","https://openalex.org/W6798597329","https://openalex.org/W6802546489","https://openalex.org/W6803752119","https://openalex.org/W6804120432","https://openalex.org/W6810319077","https://openalex.org/W6838596489"],"related_works":["https://openalex.org/W2186284405","https://openalex.org/W4281690070","https://openalex.org/W4287497346","https://openalex.org/W2794438528","https://openalex.org/W2181773877","https://openalex.org/W2110108310","https://openalex.org/W2358020347","https://openalex.org/W2537969829","https://openalex.org/W2145908128","https://openalex.org/W2766531837"],"abstract_inverted_index":{"We":[0,50,69],"introduce":[1],"a":[2,35],"framework":[3,32],"that":[4,107],"recommends":[5],"music":[6,46],"based":[7],"on":[8,34,59],"the":[9,41,83,92,98,108],"emotions":[10],"of":[11],"speech.":[12],"In":[13],"content":[14],"creation":[15],"and":[16,45,55,66],"daily":[17],"life,":[18],"speech":[19,44,53,61],"contains":[20],"information":[21],"about":[22],"human":[23],"emotions,":[24],"which":[25],"can":[26],"be":[27],"enhanced":[28],"by":[29],"music.":[30],"Our":[31,102],"focuses":[33],"cross-domain":[36,78],"retrieval":[37,79],"system":[38],"to":[39],"bridge":[40],"gap":[42],"between":[43],"via":[47],"emotion":[48,73,93],"labels.":[49],"explore":[51],"different":[52,60],"representations":[54],"report":[56],"their":[57],"impact":[58],"types,":[62],"including":[63],"acting":[64],"voice":[65],"wake-up":[67],"words.":[68],"also":[70],"propose":[71],"an":[72],"similarity":[74],"regularization":[75,84],"term":[76,85],"in":[77,91,97,113],"tasks.":[80],"By":[81],"incorporating":[82],"into":[86],"training,":[87],"similar":[88],"speech-and-music":[89],"pairs":[90],"space":[94],"are":[95],"closer":[96],"joint":[99],"embedding":[100],"space.":[101],"comprehensive":[103],"experimental":[104],"results":[105],"show":[106],"proposed":[109],"model":[110],"is":[111],"effective":[112],"textless":[114],"speech-to-music":[115],"retrieval.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}