{"id":"https://openalex.org/W7148554620","doi":"https://doi.org/10.1109/asru65441.2025.11434802","title":"USAD: Universal Speech and Audio Representation via Distillation","display_name":"USAD: Universal Speech and Audio Representation via Distillation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148554620","doi":"https://doi.org/10.1109/asru65441.2025.11434802"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434802","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/A5078976109","display_name":"Heng-Jui Chang","orcid":"https://orcid.org/0000-0002-1690-2610"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Heng-Jui Chang","raw_affiliation_strings":["MIT CSAIL,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL,Cambridge,MA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabhchand Bhati","raw_affiliation_strings":["MIT CSAIL,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL,Cambridge,MA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132824681","display_name":"James R. Glass","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT CSAIL,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL,Cambridge,MA,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132797692","display_name":"Alexander H. Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander H. Liu","raw_affiliation_strings":["MIT CSAIL,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL,Cambridge,MA,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078976109"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87577216,"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":0.5234000086784363,"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":0.5234000086784363,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1177000030875206,"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/T11309","display_name":"Music and Audio Processing","score":0.07620000094175339,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5256999731063843},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5144000053405762},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5105999708175659},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4763999879360199},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.47130000591278076},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4334000051021576},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.40610000491142273},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.39629998803138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634999752044678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6991999745368958},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5256999731063843},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5144000053405762},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.39629998803138733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.2768000066280365},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434802","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","score":0.5733808875083923,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2933138175","https://openalex.org/W2963925437","https://openalex.org/W2995181338","https://openalex.org/W3045349544","https://openalex.org/W3095410713","https://openalex.org/W3119308075","https://openalex.org/W3139878283","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3201143670","https://openalex.org/W3203140070","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226380987","https://openalex.org/W4285250921","https://openalex.org/W4297841853","https://openalex.org/W4372260310","https://openalex.org/W4372341324","https://openalex.org/W4375869224","https://openalex.org/W4385823182","https://openalex.org/W4390738640","https://openalex.org/W4391021627","https://openalex.org/W4392909098","https://openalex.org/W4394862910","https://openalex.org/W4404784428","https://openalex.org/W4406461568","https://openalex.org/W4415433234","https://openalex.org/W4415433654","https://openalex.org/W4415433959"],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,36],"(SSL)":[2],"has":[3],"revolutionized":[4],"audio":[5,34,40,64,82],"representations,":[6],"yet":[7],"models":[8,56],"often":[9],"remain":[10],"domain-specific,":[11],"focusing":[12],"on":[13,61,95],"either":[14],"speech":[15,79],"or":[16],"non-speech":[17],"tasks.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"present":[23],"Universal":[24],"Speech":[25],"and":[26,43,73,77,84,97],"Audio":[27],"Distillation":[28],"(USAD),":[29],"a":[30,45,59,62,92],"unified":[31],"approach":[32],"to":[33,57],"representation":[35],"that":[37],"integrates":[38],"diverse":[39],"types\u2014speech,":[41],"sound,":[42],"music\u2014into":[44],"single":[46,93],"model.":[47],"USAD":[48,66],"employs":[49],"efficient":[50],"layer-to-layer":[51],"distillation":[52],"from":[53],"domain-specific":[54],"SSL":[55],"train":[58],"student":[60],"comprehensive":[63],"dataset.":[65],"offers":[67],"competitive":[68],"performance":[69],"across":[70],"various":[71],"benchmarks":[72],"datasets,":[74],"including":[75],"frame":[76],"instance-level":[78],"processing":[80],"tasks,":[81],"tagging,":[83],"sound":[85],"classification,":[86],"achieving":[87],"near":[88],"state-of-the-art":[89],"results":[90],"with":[91],"encoder":[94],"SUPERB":[96],"HEAR":[98],"benchmarks.<sup":[99],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[100,102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>Models:":[103],"https://huggingface.co/MIT-SLS/USAD-Base":[104]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}