{"id":"https://openalex.org/W4319862265","doi":"https://doi.org/10.1109/slt54892.2023.10023147","title":"An Analysis of Semantically-Aligned Speech-Text Embeddings","display_name":"An Analysis of Semantically-Aligned Speech-Text Embeddings","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862265","doi":"https://doi.org/10.1109/slt54892.2023.10023147"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023147","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5112588637","display_name":"Muhammad Huzaifah","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Muhammad Huzaifah","raw_affiliation_strings":["Institute for Infocomm Research,Agency for Science, Technology and Research,Singapore","Agency for Science, Technology and Research, Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,Agency for Science, Technology and Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Agency for Science, Technology and Research, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083404931","display_name":"Ivan Kukanov","orcid":"https://orcid.org/0000-0003-4052-2754"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ivan Kukanov","raw_affiliation_strings":["Institute for Infocomm Research,Agency for Science, Technology and Research,Singapore","Agency for Science, Technology and Research, Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,Agency for Science, Technology and Research,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Agency for Science, Technology and Research, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8318,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69670443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"747","last_page":"754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.7715148329734802},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7238935232162476},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6534656286239624},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6519486904144287},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6325856447219849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557633101940155},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.536584198474884},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5347048044204712},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.523775041103363},{"id":"https://openalex.org/keywords/semantic-space","display_name":"Semantic space","score":0.5088334679603577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47746542096138},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4588949680328369},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4542470872402191},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15282312035560608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715148329734802},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7238935232162476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6534656286239624},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6519486904144287},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6325856447219849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557633101940155},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.536584198474884},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5347048044204712},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.523775041103363},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.5088334679603577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47746542096138},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4588949680328369},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4542470872402191},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15282312035560608},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023147","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1494198834","https://openalex.org/W2252211741","https://openalex.org/W2593390416","https://openalex.org/W2750779823","https://openalex.org/W2797583228","https://openalex.org/W2804648901","https://openalex.org/W2872172641","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2940092410","https://openalex.org/W2962739339","https://openalex.org/W2964204621","https://openalex.org/W2965373594","https://openalex.org/W2988217457","https://openalex.org/W3036601975","https://openalex.org/W3092424727","https://openalex.org/W3096109555","https://openalex.org/W3096589040","https://openalex.org/W3113908264","https://openalex.org/W3127686677","https://openalex.org/W3148001440","https://openalex.org/W3176455679","https://openalex.org/W3176711365","https://openalex.org/W3196833881","https://openalex.org/W3209059054","https://openalex.org/W3213018012","https://openalex.org/W4226380987","https://openalex.org/W4294170691","https://openalex.org/W6726295259","https://openalex.org/W6750665317","https://openalex.org/W6751433836","https://openalex.org/W6753441104","https://openalex.org/W6757635932","https://openalex.org/W6773238793","https://openalex.org/W6780218876","https://openalex.org/W6784050962","https://openalex.org/W6789693907","https://openalex.org/W6789826613","https://openalex.org/W6790019176","https://openalex.org/W6803675045"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3191326035","https://openalex.org/W3140002740","https://openalex.org/W4226361842","https://openalex.org/W2255924030","https://openalex.org/W4210441873","https://openalex.org/W3156761522","https://openalex.org/W3034658947"],"abstract_inverted_index":{"Embeddings":[0],"play":[1],"an":[2],"important":[3],"role":[4],"in":[5,62,93],"end-to-end":[6],"solutions":[7],"for":[8,70,109,114],"multi-modal":[9],"language":[10],"processing":[11],"problems.":[12],"Although":[13],"there":[14],"has":[15],"been":[16],"some":[17,42],"effort":[18],"to":[19,121,131],"understand":[20],"the":[21,54,119,123],"properties":[22,44],"of":[23,29,45,118,125],"single-modality":[24],"embedding":[25,49],"spaces,":[26],"particularly":[27],"that":[28,67,77],"text,":[30],"their":[31],"cross-modal":[32,100],"counterparts":[33],"are":[34,68],"less":[35],"understood.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,102],"study":[41],"intrinsic":[43],"a":[46,63,104],"joint":[47],"speech-text":[48],"space,":[50],"constructed":[51],"by":[52],"minimizing":[53],"distance":[55],"between":[56],"paired":[57],"utterance":[58],"and":[59,85,116],"transcription":[60],"inputs":[61],"teacher-student":[64],"model":[65],"setup,":[66],"informative":[69],"several":[71],"prominent":[72],"use":[73],"cases.":[74],"We":[75],"found":[76],"incorporating":[78],"automatic":[79],"speech":[80],"recognition":[81],"through":[82],"both":[83],"pretraining":[84],"multitask":[86],"scenarios":[87],"aid":[88],"semantic":[89,110],"alignment":[90],"significantly,":[91],"resulting":[92],"more":[94],"tightly":[95],"coupled":[96],"embeddings.":[97],"To":[98],"analyse":[99],"embeddings":[101],"utilise":[103],"quantitative":[105],"retrieval":[106],"accuracy":[107],"metric":[108],"alignment,":[111],"zero-shot":[112],"classification":[113],"generalis-ability,":[115],"probing":[117],"encoders":[120],"observe":[122],"extent":[124],"knowledge":[126],"transfer":[127],"from":[128],"one":[129],"modality":[130],"another.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}