{"id":"https://openalex.org/W4372338352","doi":"https://doi.org/10.1109/icassp49357.2023.10094658","title":"SLBERT: A Novel Pre-Training Framework for Joint Speech and Language Modeling","display_name":"SLBERT: A Novel Pre-Training Framework for Joint Speech and Language Modeling","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372338352","doi":"https://doi.org/10.1109/icassp49357.2023.10094658"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094658","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094658","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/A5004353809","display_name":"Onkar Susladkar","orcid":"https://orcid.org/0000-0003-4511-1858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Onkar Susladkar","raw_affiliation_strings":["Natter Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Natter Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013597720","display_name":"Prajwal Gatti","orcid":"https://orcid.org/0000-0002-6554-3132"},"institutions":[{"id":"https://openalex.org/I4405260736","display_name":"Dayananda Sagar College of Engineering","ror":"https://ror.org/046qksq74","country_code":"IN","type":"education","lineage":["https://openalex.org/I4400573291","https://openalex.org/I4405260736"]},{"id":"https://openalex.org/I8977528","display_name":"Dr. Hari Singh Gour University","ror":"https://ror.org/01xapxe37","country_code":"IN","type":"education","lineage":["https://openalex.org/I8977528"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prajwal Gatti","raw_affiliation_strings":["Dayananda Sagar College of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dayananda Sagar College of Engineering","institution_ids":["https://openalex.org/I4405260736","https://openalex.org/I8977528"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044103955","display_name":"Santosh Kumar Yadav","orcid":"https://orcid.org/0000-0001-8755-699X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santosh Kumar Yadav","raw_affiliation_strings":["Natter Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Natter Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3928497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.8987746238708496},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6435627341270447},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6244845390319824},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5762725472450256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5732181668281555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5385445356369019},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5318348407745361},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4806027114391327},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4316468834877014},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42042064666748047},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10955652594566345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8987746238708496},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6435627341270447},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6244845390319824},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5762725472450256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5732181668281555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385445356369019},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5318348407745361},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4806027114391327},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4316468834877014},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42042064666748047},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10955652594566345},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094658","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094658","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1649407914","https://openalex.org/W2786839803","https://openalex.org/W2891229414","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2945260553","https://openalex.org/W2964303773","https://openalex.org/W2965373594","https://openalex.org/W2966715458","https://openalex.org/W2972584841","https://openalex.org/W3007282427","https://openalex.org/W3015558147","https://openalex.org/W3034266838","https://openalex.org/W3045969489","https://openalex.org/W3093051361","https://openalex.org/W3096109555","https://openalex.org/W3126721948","https://openalex.org/W3204105917","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225307240","https://openalex.org/W4286909684","https://openalex.org/W4319300185","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6759579507","https://openalex.org/W6762122294","https://openalex.org/W6766673545","https://openalex.org/W6766904570","https://openalex.org/W6802191880"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"We":[0,23,87],"propose":[1],"SLBERT":[2,73],"(Speech":[3],"and":[4,20,39,67,84,99],"Language":[5,79],"pre-training":[6],"framework":[7,13],"for":[8,14,65],"BERT),":[9],"an":[10],"end-to-end":[11],"trainable":[12],"learning":[15],"joint":[16],"representations":[17,64],"of":[18],"speech":[19,38,66],"language":[21,40,68],"modalities.":[22],"enhance":[24],"the":[25,48],"well-known":[26,94],"BERT":[27],"architecture":[28,34],"to":[29],"provide":[30],"a":[31,53],"dual-stream":[32],"multimodal":[33,95],"that":[35],"processes":[36],"both":[37,108],"input.":[41],"To":[42,60],"enable":[43],"effective":[44],"information":[45],"exchange":[46],"between":[47],"two":[49,93],"modalities,":[50],"we":[51,71],"introduce":[52],"novel":[54],"attention":[55],"fusion":[56],"mechanism":[57],"via":[58],"AF-Blocks.":[59],"acquire":[61],"robust":[62],"contrastive":[63],"processing":[69],"applications,":[70],"pre-train":[72],"on":[74,92,107],"three":[75],"auxiliary":[76],"tasks:":[77,96],"Masked":[78,81],"Modeling,":[80,83],"Speech":[82],"Speech-Language":[85],"Matching.":[86],"evaluate":[88],"our":[89],"proposed":[90],"model":[91,103],"intent":[97],"classification":[98],"sentiment":[100],"analysis.":[101],"Our":[102],"achieves":[104],"state-of-the-art":[105],"results":[106],"benchmarks":[109],"while":[110],"surpassing":[111],"even":[112],"larger":[113],"baselines.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}