{"id":"https://openalex.org/W4403667065","doi":"https://doi.org/10.48550/arxiv.2409.09289","title":"DSCLAP: Domain-Specific Contrastive Language-Audio Pre-Training","display_name":"DSCLAP: Domain-Specific Contrastive Language-Audio Pre-Training","publication_year":2024,"publication_date":"2024-09-14","ids":{"openalex":"https://openalex.org/W4403667065","doi":"https://doi.org/10.48550/arxiv.2409.09289"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.09289","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.09289","pdf_url":"https://arxiv.org/pdf/2409.09289","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.09289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103086479","display_name":"Shengqiang Liu","orcid":"https://orcid.org/0009-0009-6003-9146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shengqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384551","display_name":"Da Liu","orcid":"https://orcid.org/0000-0003-0816-1901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Da","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043482575","display_name":"Anna Wang","orcid":"https://orcid.org/0000-0001-9905-767X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Anna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Zhiyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073887901","display_name":"Jie Gao","orcid":"https://orcid.org/0000-0002-5601-2858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100346266","display_name":"Yali Li","orcid":"https://orcid.org/0000-0002-6629-7228"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9585999846458435,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9585999846458435,"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":0.9498000144958496,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9272000193595886,"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/computer-science","display_name":"Computer science","score":0.6604741811752319},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5770138502120972},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5245164632797241},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48170119524002075},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.41521698236465454},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36616113781929016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10249724984169006},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.04250466823577881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604741811752319},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5770138502120972},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5245164632797241},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48170119524002075},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.41521698236465454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36616113781929016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10249724984169006},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.04250466823577881},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.09289","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.09289","pdf_url":"https://arxiv.org/pdf/2409.09289","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.09289","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.09289","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.09289","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.09289","pdf_url":"https://arxiv.org/pdf/2409.09289","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403667065.pdf","grobid_xml":"https://content.openalex.org/works/W4403667065.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Analyzing":[0],"real-world":[1],"multimodal":[2],"signals":[3,112],"is":[4,64],"an":[5,116],"essential":[6],"and":[7,31,40,67,94,119,125,134],"challenging":[8],"task":[9],"for":[10,53,170],"intelligent":[11],"voice":[12],"assistants":[13],"(IVAs).":[14],"Mainstream":[15],"approaches":[16],"have":[17],"achieved":[18],"remarkable":[19],"performance":[20],"on":[21,42,140,149],"various":[22],"downstream":[23,54,151],"tasks":[24,43,152],"of":[25,143],"IVAs":[26,172],"with":[27,101],"pre-trained":[28,38],"audio":[29,70,104,111,133],"models":[30,36,163],"text":[32,114],"models.":[33],"However,":[34],"these":[35,87],"are":[37],"independently":[39],"usually":[41],"different":[44],"from":[45],"target":[46],"domains,":[47,59],"resulting":[48],"in":[49,57,164],"sub-optimal":[50],"modality":[51],"representations":[52],"tasks.":[55],"Moreover,":[56],"many":[58],"collecting":[60],"enough":[61],"language-audio":[62,99,127],"pairs":[63],"extremely":[65],"hard,":[66],"transcribing":[68],"raw":[69,103,110],"also":[71],"requires":[72],"high":[73],"professional":[74],"skills,":[75],"making":[76],"it":[77],"difficult":[78],"or":[79],"even":[80],"infeasible":[81],"to":[82,130],"joint":[83],"pre-training.":[84],"To":[85],"address":[86],"painpoints,":[88],"we":[89],"propose":[90],"DSCLAP,":[91],"a":[92,121,126],"simple":[93],"effective":[95],"framework":[96],"that":[97,154],"enables":[98],"pre-training":[100],"only":[102],"signal":[105],"input.":[106],"Specifically,":[107],"DSCLAP":[108,139,158],"converts":[109],"into":[113],"via":[115],"ASR":[117,135],"system":[118],"combines":[120],"contrastive":[122],"learning":[123],"objective":[124,129],"matching":[128],"align":[131],"the":[132,161],"transcriptions.":[136],"We":[137],"pre-train":[138],"12,107":[141],"hours":[142],"in-vehicle":[144],"domain":[145],"audio.":[146],"Empirical":[147],"results":[148],"two":[150],"show":[153],"while":[155],"conceptually":[156],"simple,":[157],"significantly":[159],"outperforms":[160],"baseline":[162],"all":[165],"metrics,":[166],"showing":[167],"great":[168],"promise":[169],"domain-specific":[171],"applications.":[173]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}