{"id":"https://openalex.org/W7155103802","doi":"https://doi.org/10.1109/icassp55912.2026.11462214","title":"WavLink: Compact Audio\u2013Text Embeddings with a Global Whisper Token","display_name":"WavLink: Compact Audio\u2013Text Embeddings with a Global Whisper Token","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155103802","doi":"https://doi.org/10.1109/icassp55912.2026.11462214"},"language":"en","primary_location":{"id":"doi:10.1109/icassp55912.2026.11462214","doi":"https://doi.org/10.1109/icassp55912.2026.11462214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462214","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.15118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048139334","display_name":"Gokul Karthik Kumar","orcid":"https://orcid.org/0000-0003-2848-7095","observed_orcids":["https://orcid.org/0000-0003-2848-7095"]},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Gokul Karthik Kumar","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020952319","display_name":"Ludovick Lepauloux","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ludovick Lepauloux","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013316111","display_name":"Hakim Hacid","orcid":"https://orcid.org/0000-0003-2265-9343","observed_orcids":["https://orcid.org/0000-0003-2265-9343"]},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hakim Hacid","raw_affiliation_strings":["Technology Innovation Institute,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology Innovation Institute,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210087059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210087059"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22387775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1581","last_page":"1585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9243000149726868,"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":0.9243000149726868,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.030300000682473183,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.026599999517202377,"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/whisper","display_name":"Whisper","score":0.7419999837875366},{"id":"https://openalex.org/keywords/audio-retrieval","display_name":"audio retrieval","score":0.5379999876022339},{"id":"https://openalex.org/keywords/clap","display_name":"CLAP","score":0.609000027179718},{"id":"https://openalex.org/keywords/audio-visual-question-answering","display_name":"audio-visual question answering","score":0.40400001406669617},{"id":"https://openalex.org/keywords/two-stage-training","display_name":"two-stage training","score":0.7350000143051147},{"id":"https://openalex.org/keywords/zero-shot-classification","display_name":"zero-shot classification","score":0.7540000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5630999803543091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35109999775886536},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3456000089645386},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31360000371932983},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp55912.2026.11462214","doi":"https://doi.org/10.1109/icassp55912.2026.11462214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp55912.2026.11462214","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.15118","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.15118","pdf_url":"https://arxiv.org/pdf/2601.15118","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,"listed_in":[],"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.2601.15118","doi":"https://doi.org/10.48550/arxiv.2601.15118","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.15118","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.15118","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.15118","pdf_url":"https://arxiv.org/pdf/2601.15118","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155103802.pdf","grobid_xml":"https://content.openalex.org/works/W7155103802.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2981182029","https://openalex.org/W3015371781","https://openalex.org/W3205475937","https://openalex.org/W4226442948","https://openalex.org/W4372260310","https://openalex.org/W4385807453","https://openalex.org/W4390873312","https://openalex.org/W4392903801","https://openalex.org/W4402576566","https://openalex.org/W4402684170","https://openalex.org/W4403780823","https://openalex.org/W4408352515","https://openalex.org/W4411688496","https://openalex.org/W4412886823","https://openalex.org/W7148468420"],"related_works":["https://openalex.org/W4385822467","https://openalex.org/W4392902953","https://openalex.org/W3210447534","https://openalex.org/W4200047557","https://openalex.org/W4388685229","https://openalex.org/W7154362176","https://openalex.org/W7005522851","https://openalex.org/W7131126719","https://openalex.org/W7138244753","https://openalex.org/W4391021645"],"abstract_inverted_index":{"Whisper":[0,52,64],"has":[1],"become":[2],"the":[3],"de-facto":[4],"encoder":[5,65],"for":[6],"extracting":[7],"general-purpose":[8],"audio":[9,43],"features":[10,25],"in":[11],"large":[12],"audio\u2013language":[13],"models,":[14],"where":[15],"a":[16,57,67,74,78],"30-second":[17],"clip":[18],"is":[19],"typically":[20],"represented":[21],"by":[22],"1500":[23],"frame":[24],"projected":[26],"into":[27],"an":[28],"LLM.":[29],"In":[30],"contrast,":[31],"audio\u2013text":[32,59],"embedding":[33,60],"models":[34,37],"like":[35],"CLAP-based":[36],"have":[38,49],"largely":[39],"relied":[40],"on":[41,130],"alternative":[42],"encoders":[44],"(e.g.,":[45],"HTS-AT,":[46],"PaSST),":[47],"and":[48,92,134],"not":[50],"leveraged":[51],"effectively.":[53],"We":[54],"present":[55],"WavLink,":[56],"compact":[58],"model":[61,109],"that":[62,98],"augments":[63],"with":[66,73,112,121,132],"learnable":[68],"global":[69],"token,":[70],"trained":[71],"jointly":[72],"text":[75,86],"encoder.":[76],"Through":[77],"systematic":[79],"study":[80],"of":[81],"design":[82],"choices,":[83],"including":[84],"pretrained":[85],"encoders,":[87],"loss":[88],"functions,":[89],"training":[90,105],"modes,":[91],"data":[93],"mixtures,":[94],"we":[95],"identify":[96],"configurations":[97],"yield":[99],"state-of-the-art":[100],"retrieval":[101],"performance.":[102],"Our":[103],"two-stage":[104],"recipe":[106],"across":[107],"three":[108],"sizes,":[110],"combined":[111],"Matryoshka-style":[113],"supervision,":[114],"improves":[115],"scalability,":[116],"enabling":[117],"8\u00d7":[118],"smaller":[119],"embeddings":[120],"minimal":[122],"performance":[123,129],"drop.":[124],"WavLink":[125],"also":[126],"demonstrates":[127],"competitive":[128],"AIR-Bench":[131],"MCQs":[133],"zero-shot":[135],"classification.":[136]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-04-22T00:00:00"}
