{"id":"https://openalex.org/W4387714135","doi":"https://doi.org/10.1145/3614008.3614015","title":"DistilALHuBERT: A Distilled Parameter Sharing Audio Representation Model","display_name":"DistilALHuBERT: A Distilled Parameter Sharing Audio Representation Model","publication_year":2023,"publication_date":"2023-07-14","ids":{"openalex":"https://openalex.org/W4387714135","doi":"https://doi.org/10.1145/3614008.3614015"},"language":"en","primary_location":{"id":"doi:10.1145/3614008.3614015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3614008.3614015","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3614008.3614015","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Signal Processing and Machine Learning (SPML)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3614008.3614015","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034166666","display_name":"Haoyu Wang","orcid":"https://orcid.org/0009-0000-9167-2459"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0000-9167-2459","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052457932","display_name":"Siyuan Wang","orcid":"https://orcid.org/0009-0007-0934-1572"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0009-0007-0934-1572","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012489033","display_name":"Yaguang Gong","orcid":"https://orcid.org/0009-0009-6502-9262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaguang Gong","raw_affiliation_strings":["TAL Education, China"],"raw_orcid":"https://orcid.org/0009-0009-6502-9262","affiliations":[{"raw_affiliation_string":"TAL Education, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-3841-1959","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13297016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8038776516914368},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6966133713722229},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5848827958106995},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5320196151733398},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44155919551849365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3929242789745331},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33304107189178467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3299192190170288},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09682941436767578},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08807367086410522},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07830137014389038}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038776516914368},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6966133713722229},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5848827958106995},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5320196151733398},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44155919551849365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929242789745331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33304107189178467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3299192190170288},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09682941436767578},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08807367086410522},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07830137014389038},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3614008.3614015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3614008.3614015","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3614008.3614015","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Signal Processing and Machine Learning (SPML)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3614008.3614015","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3614008.3614015","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3614008.3614015","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th International Conference on Signal Processing and Machine Learning (SPML)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1014351457","display_name":null,"funder_award_id":"62276153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3155635598","display_name":null,"funder_award_id":"2020AAA0104500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387714135.pdf","grobid_xml":"https://content.openalex.org/works/W4387714135.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2866343820","https://openalex.org/W2982223350","https://openalex.org/W2990714382","https://openalex.org/W2996428491","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3095221623","https://openalex.org/W3203140070","https://openalex.org/W3205644108","https://openalex.org/W3208632377","https://openalex.org/W3209059054","https://openalex.org/W4285144981","https://openalex.org/W4297841280"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175"],"abstract_inverted_index":{"Self-supervised":[0],"pre-trained":[1,27,58],"audio":[2,76],"representation":[3,77],"models":[4,28,59,106],"such":[5],"as":[6],"Wav2vec":[7],"or":[8],"HuBERT":[9],"have":[10,44],"brought":[11],"notable":[12],"improvements":[13],"to":[14,32],"many":[15],"downstream":[16],"audio-related":[17],"tasks,":[18],"but":[19],"the":[20,55,64,85,94,98],"huge":[21],"number":[22,100],"of":[23,25,57,63,101],"parameters":[24],"these":[26],"sets":[29],"a":[30,72],"barrier":[31],"their":[33],"application":[34],"on":[35,84],"memory-constrained":[36],"edge":[37],"devices.":[38],"Recursive":[39],"Transformers,":[40],"represented":[41],"by":[42],"Albert,":[43],"proven":[45],"that":[46,89],"parameter":[47],"sharing":[48],"through":[49],"transformer":[50,75],"layers":[51],"can":[52,91],"obviously":[53],"reduce":[54],"size":[56],"while":[60],"maintaining":[61],"most":[62],"performance.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"propose":[70],"DistilALHuBERT,":[71],"lightweight":[73],"recursive":[74],"model":[78,96],"distilled":[79],"from":[80],"Hubert.":[81],"Evaluation":[82],"results":[83],"S3PRL":[86],"benchmark":[87],"show":[88],"DistilALHuBERT":[90],"significantly":[92],"outperform":[93],"DistilHuBERT":[95],"with":[97],"same":[99],"parameters.":[102],"Our":[103],"code":[104],"and":[105],"are":[107],"available":[108],"at":[109],"https://github.com/backspacetg/distilAlhubert.":[110]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}