{"id":"https://openalex.org/W4226390724","doi":"https://doi.org/10.21437/interspeech.2022-10839","title":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","display_name":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226390724","doi":"https://doi.org/10.21437/interspeech.2022-10839"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10839","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10839","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","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/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, JAPAN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, JAPAN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3819","last_page":"3823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9954000115394592,"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":0.9517999887466431,"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":0.7427359819412231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7292313575744629},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6321588754653931},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.520544171333313},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4628296196460724},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4548216462135315},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4535277485847473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4134443402290344},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41142377257347107},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06359648704528809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427359819412231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7292313575744629},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6321588754653931},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.520544171333313},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4628296196460724},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4548216462135315},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4535277485847473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4134443402290344},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41142377257347107},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06359648704528809},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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:10.21437/interspeech.2022-10839","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10839","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G367708065","display_name":null,"funder_award_id":"ACI-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3709464396","display_name":null,"funder_award_id":"-1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3730782400","display_name":"XSEDE 2.0:  Integrating, Enabling and Enhancing National Cyberinfrastructure with Expanding Community Involvement","funder_award_id":"1548562","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7404166632","display_name":"Bridges: From Communities and Data to Workflows and Insight","funder_award_id":"1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8729765517","display_name":null,"funder_award_id":"ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W2042141988","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2510867321","https://openalex.org/W2526425061","https://openalex.org/W2559260703","https://openalex.org/W2936774411","https://openalex.org/W2937484199","https://openalex.org/W2952218014","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2962892438","https://openalex.org/W2962935966","https://openalex.org/W2963980003","https://openalex.org/W2995181338","https://openalex.org/W2998616931","https://openalex.org/W3015199127","https://openalex.org/W3032514799","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3119308075","https://openalex.org/W3160799772","https://openalex.org/W3209984917","https://openalex.org/W4221138681","https://openalex.org/W4226380987","https://openalex.org/W4285761032","https://openalex.org/W4286893829","https://openalex.org/W4287120025","https://openalex.org/W4287989344","https://openalex.org/W4297841603"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2184127972","https://openalex.org/W2118159520","https://openalex.org/W2307514504","https://openalex.org/W2771275309","https://openalex.org/W3163142165","https://openalex.org/W1819595055","https://openalex.org/W1799027130","https://openalex.org/W3041694242"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"our":[3],"end-to-end":[4],"(E2E)":[5],"automatic":[6],"speech":[7,14,18,22,44,68,73],"recognition":[8,74],"(ASR)":[9],"model":[10,37,96],"targetting":[11],"at":[12],"robust":[13],"recognition,":[15],"called":[16],"Integraded":[17],"Recognition":[19],"with":[20,29],"enhanced":[21,67],"Input":[23],"for":[24,72,105,111,117],"Self-supervised":[25],"learning":[26,51,84],"representation":[27,52],"(IRIS).Compared":[28],"conventional":[30],"E2E":[31,36],"ASR":[32],"models,":[33],"the":[34,58,61,77,88,94,98,103,106,112,118,123,129],"proposed":[35,78],"integrates":[38],"two":[39],"important":[40],"modules":[41],"including":[42],"a":[43,49],"enhancement":[45],"(SE)":[46],"module":[47,56,63,127],"and":[48,115,128],"self-supervised":[50],"(SSLR)":[53],"module.The":[54],"SE":[55,131],"enhances":[57],"noisy":[59],"speech.Then":[60],"SSLR":[62,126],"extracts":[64],"features":[65],"from":[66],"to":[69,122],"be":[70],"used":[71],"(ASR).To":[75],"train":[76],"model,":[79],"we":[80],"establish":[81],"an":[82],"efficient":[83],"scheme.Evaluation":[85],"results":[86],"on":[87],"monaural":[89],"CHiME-4":[90,108],"task":[91],"show":[92],"that":[93],"IRIS":[95],"achieves":[97],"best":[99],"performance":[100],"reported":[101],"in":[102],"literature":[104],"single-channel":[107],"benchmark":[109],"(2.0%":[110],"real":[113,119],"development":[114],"3.9%":[116],"test)":[120],"thanks":[121],"powerful":[124],"pre-trained":[125],"finetuned":[130],"module.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":15}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}