{"id":"https://openalex.org/W4375868755","doi":"https://doi.org/10.1109/icassp49357.2023.10095130","title":"Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition","display_name":"Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868755","doi":"https://doi.org/10.1109/icassp49357.2023.10095130"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095130","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095130","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/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039664887","display_name":"Changli Tang","orcid":"https://orcid.org/0000-0002-6550-1901"},"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":"Changli Tang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733455","display_name":"Yujin Wang","orcid":"https://orcid.org/0000-0001-5982-4088"},"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":"Yujin Wang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068357345","display_name":"Zhisheng Zheng","orcid":"https://orcid.org/0000-0001-7761-9790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisheng Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/front-and-back-ends","display_name":"Front and back ends","score":0.8266773223876953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756197452545166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6970903873443604},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.662461519241333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4428120255470276},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.42280250787734985},{"id":"https://openalex.org/keywords/front","display_name":"Front (military)","score":0.4114835858345032},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.15517458319664001},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1065070629119873}],"concepts":[{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.8266773223876953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756197452545166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6970903873443604},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.662461519241333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4428120255470276},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.42280250787734985},{"id":"https://openalex.org/C2777551076","wikidata":"https://www.wikidata.org/wiki/Q842332","display_name":"Front (military)","level":2,"score":0.4114835858345032},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.15517458319664001},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1065070629119873},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095130","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095130","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3035060554","https://openalex.org/W3036601975","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3204696009","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4297808394","https://openalex.org/W4385823092","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6802600657","https://openalex.org/W6803164887","https://openalex.org/W6810007534","https://openalex.org/W6846509086"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W4396816926","https://openalex.org/W2593532750","https://openalex.org/W3207232378","https://openalex.org/W2642467014","https://openalex.org/W2889523925"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"a":[4,24,40,46,90],"boom":[5],"in":[6,10,23,83],"self-supervised":[7],"learning":[8],"(SSL)":[9],"various":[11],"areas":[12],"including":[13],"speech":[14,27,144],"processing.":[15],"Speech":[16],"based":[17],"SSL":[18,34,48,119,140],"models":[19,35,120,141],"present":[20],"promising":[21],"performance":[22],"range":[25],"of":[26,33,108,132],"related":[28],"tasks.":[29],"However,":[30],"the":[31,51,73,78,103,106,111,130,143],"training":[32],"is":[36,43,55,76],"computationally":[37],"expensive":[38],"and":[39,64],"common":[41],"practice":[42],"to":[44,57,96],"fine-tune":[45],"released":[47],"model":[49],"on":[50,137],"specific":[52],"task.":[53,146],"It":[54],"essential":[56],"use":[58],"consistent":[59],"front-end":[60,75,94,99,135],"input":[61],"during":[62],"pre-training":[63],"fine-tuning.":[65],"This":[66],"consistency":[67],"may":[68],"introduce":[69],"potential":[70],"issues":[71],"when":[72],"optimal":[74],"not":[77],"same":[79],"as":[80],"that":[81],"used":[82],"pre-training.":[84],"In":[85],"this":[86,98],"paper,":[87],"we":[88],"propose":[89],"simple":[91],"but":[92],"effective":[93],"adapter":[95,136],"address":[97],"discrepancy.":[100],"By":[101],"minimizing":[102],"distance":[104],"between":[105],"outputs":[107],"different":[109],"front-ends,":[110],"filterbank":[112],"feature":[113],"(Fbank)":[114],"can":[115],"be":[116],"compatible":[117],"with":[118,124],"which":[121],"are":[122],"pre-trained":[123],"waveform.":[125],"The":[126],"experiment":[127],"results":[128],"demonstrate":[129],"effectiveness":[131],"our":[133],"proposed":[134],"several":[138],"popular":[139],"for":[142],"recognition":[145]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}