{"id":"https://openalex.org/W7148351628","doi":"https://doi.org/10.1109/asru65441.2025.11434633","title":"Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style","display_name":"Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148351628","doi":"https://doi.org/10.1109/asru65441.2025.11434633"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132766648","display_name":"Wonjune Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wonjune Kang","raw_affiliation_strings":["Massachusetts Institute of Technology,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Cambridge,MA,USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132808439","display_name":"Deb Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deb Roy","raw_affiliation_strings":["Massachusetts Institute of Technology,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Cambridge,MA,USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5132766648"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87555625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.260699987411499,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.260699987411499,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.15850000083446503,"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"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.15399999916553497,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49399998784065247},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.44760000705718994},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.2824999988079071},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.2775000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5615000128746033},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5389999747276306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5295000076293945},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4043999910354614},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3513999879360199},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6133546233177185}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1815792","https://openalex.org/W1974745151","https://openalex.org/W1984076147","https://openalex.org/W2015688877","https://openalex.org/W2019211927","https://openalex.org/W2075722833","https://openalex.org/W2084339293","https://openalex.org/W2101514156","https://openalex.org/W2132464539","https://openalex.org/W2146334809","https://openalex.org/W2148986421","https://openalex.org/W2799046698","https://openalex.org/W3194782062","https://openalex.org/W3209984917","https://openalex.org/W4205742757","https://openalex.org/W4246962055","https://openalex.org/W4372260310","https://openalex.org/W4375869257","https://openalex.org/W4385822787","https://openalex.org/W4385823130","https://openalex.org/W4392902876","https://openalex.org/W4392903115","https://openalex.org/W4392903210","https://openalex.org/W4392903700","https://openalex.org/W4392904295","https://openalex.org/W4392908903","https://openalex.org/W4402111357","https://openalex.org/W4402111974","https://openalex.org/W4402669711","https://openalex.org/W4406611532","https://openalex.org/W4408353160","https://openalex.org/W4408353464","https://openalex.org/W4412945327"],"related_works":[],"abstract_inverted_index":{"We":[0,59,97],"introduce":[1],"the":[2,9],"task":[3],"of":[4,27,71,101,104],"expressive":[5,94],"speech":[6,14,38,61,67,95],"retrieval,":[7],"where":[8],"goal":[10],"is":[11],"to":[12,50,65,91,123],"retrieve":[13,92],"utterances":[15],"spoken":[16],"in":[17,45],"a":[18,23,75],"given":[19],"style":[20],"based":[21,40,53],"on":[22,36,41,54,128],"natural":[24],"language":[25],"description":[26],"that":[28,136],"style.":[29],"While":[30],"prior":[31],"work":[32],"has":[33],"primarily":[34],"focused":[35],"performing":[37],"retrieval":[39,141],"what":[42],"was":[43,57],"said":[44],"an":[46],"utterance,":[47],"we":[48],"aim":[49],"do":[51],"so":[52],"how":[55],"something":[56],"said.":[58],"train":[60],"and":[62,68,117],"text":[63,69,83,125],"encoders":[64],"embed":[66],"descriptions":[70],"speaking":[72,133],"styles":[73,88,134],"into":[74],"joint":[76],"latent":[77],"space,":[78],"which":[79],"enables":[80],"using":[81],"free-form":[82],"prompts":[84],"describing":[85],"emotions":[86],"or":[87],"as":[89,143],"queries":[90],"matching":[93],"segments.":[96],"perform":[98],"detailed":[99],"analyses":[100],"various":[102],"aspects":[103],"our":[105,137],"proposed":[106],"framework,":[107],"including":[108],"encoder":[109],"architectures,":[110],"training":[111],"criteria":[112],"for":[113,120],"effective":[114],"cross-modal":[115],"alignment,":[116],"prompt":[118],"augmentation":[119],"improved":[121],"generalization":[122],"arbitrary":[124],"queries.":[126],"Experiments":[127],"multiple":[129],"datasets":[130],"encompassing":[131],"22":[132],"demonstrate":[135],"approach":[138],"achieves":[139],"strong":[140],"performance":[142],"measured":[144],"by":[145],"Recall@k.":[146]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}