{"id":"https://openalex.org/W3003168191","doi":"https://doi.org/10.1109/icassp40776.2020.9053367","title":"Fully Learnable Front-End for Multi-Channel Acoustic Modeling Using Semi-Supervised Learning","display_name":"Fully Learnable Front-End for Multi-Channel Acoustic Modeling Using Semi-Supervised Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3003168191","doi":"https://doi.org/10.1109/icassp40776.2020.9053367","mag":"3003168191"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.00125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072310429","display_name":"Sanna Wager","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanna Wager","raw_affiliation_strings":["School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013650472","display_name":"Aparna Khare","orcid":"https://orcid.org/0000-0001-7151-3055"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aparna Khare","raw_affiliation_strings":["Amazon, Inc, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Amazon, Inc, Sunnyvale, CA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060740546","display_name":"Minhua Wu","orcid":"https://orcid.org/0000-0001-9798-2984"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minhua Wu","raw_affiliation_strings":["Amazon, Inc, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Amazon, Inc, Sunnyvale, CA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053915317","display_name":"Kenichi Kumatani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenichi Kumatani","raw_affiliation_strings":["Amazon, Inc, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Amazon, Inc, Sunnyvale, CA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["Amazon, Inc, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Amazon, Inc, Sunnyvale, CA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072310429"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39403259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1050","issue":null,"first_page":"6864","last_page":"6868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.7748059034347534},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6915662884712219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6890259385108948},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6221289038658142},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5862223505973816},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5729180574417114},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5593095421791077},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.48899757862091064},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.48264914751052856},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.471874862909317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46776196360588074},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.432316392660141},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42653948068618774},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38725417852401733},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10183262825012207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10082739591598511},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09071779251098633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748059034347534},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6915662884712219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6890259385108948},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6221289038658142},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5862223505973816},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5729180574417114},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5593095421791077},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48899757862091064},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.48264914751052856},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.471874862909317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46776196360588074},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.432316392660141},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42653948068618774},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38725417852401733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10183262825012207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10082739591598511},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09071779251098633},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.00125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00125","pdf_url":"https://arxiv.org/pdf/2002.00125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.00125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00125","pdf_url":"https://arxiv.org/pdf/2002.00125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1515932869","https://openalex.org/W1533861849","https://openalex.org/W1821462560","https://openalex.org/W2057035781","https://openalex.org/W2061074721","https://openalex.org/W2100693051","https://openalex.org/W2129227482","https://openalex.org/W2132297779","https://openalex.org/W2291522532","https://openalex.org/W2402040300","https://openalex.org/W2539797148","https://openalex.org/W2589857635","https://openalex.org/W2600628583","https://openalex.org/W2787290364","https://openalex.org/W2910715461","https://openalex.org/W2921214093","https://openalex.org/W2921496354","https://openalex.org/W2954695182","https://openalex.org/W2962894366","https://openalex.org/W2962907457","https://openalex.org/W2963376890","https://openalex.org/W4206633762","https://openalex.org/W6631943919","https://openalex.org/W6638523607","https://openalex.org/W6712847557","https://openalex.org/W6728770099","https://openalex.org/W6735168207","https://openalex.org/W6748052321","https://openalex.org/W6760911985","https://openalex.org/W6763847309"],"related_works":["https://openalex.org/W2021595906","https://openalex.org/W2766087987","https://openalex.org/W1606020025","https://openalex.org/W106304674","https://openalex.org/W2095992409","https://openalex.org/W2357857030","https://openalex.org/W2035826164","https://openalex.org/W2063491684","https://openalex.org/W2038621399","https://openalex.org/W3045896262"],"abstract_inverted_index":{"In":[0,70],"this":[1],"work,":[2],"we":[3,33],"investigated":[4,108],"the":[5,43,48,56,64,67,109,113,119,134,156],"teacher-student":[6,163],"training":[7,164],"paradigm":[8],"to":[9,74,117,142,172],"train":[10],"a":[11,24,35,75,86,143,149,166],"fully":[12],"learnable":[13],"multi-channel":[14,37,51,114,144],"acoustic":[15,39],"model":[16,28,40,77,145],"for":[17,155],"far-field":[18],"automatic":[19],"speech":[20,44],"recognition":[21,45],"(ASR).":[22],"Using":[23],"large":[25],"offline":[26],"teacher":[27,68],"trained":[29,34,62,78],"on":[30,79],"beamformed":[31,120],"audio,":[32],"simpler":[36],"student":[38],"used":[41],"in":[42],"system.":[46],"For":[47],"student,":[49],"both":[50],"feature":[52],"extraction":[53],"layers":[54,59],"and":[55,151,162],"higher":[57],"classification":[58],"were":[60],"jointly":[61],"using":[63,98,126],"logits":[65],"from":[66],"model.":[69],"our":[71,173],"experiments,":[72],"compared":[73,141,171],"baseline":[76],"about":[80,93],"600":[81],"hours":[82,102],"of":[83,92,103,111,169],"transcribed":[84],"data,":[85],"relative":[87],"word-error":[88],"rate":[89,137],"(WER)":[90],"reduction":[91,168],"27.3%":[94],"was":[95],"achieved":[96],"when":[97,140],"an":[99],"additional":[100],"1800":[101],"untran-scribed":[104],"data.":[105],"We":[106,129],"also":[107],"benefit":[110],"pre-training":[112,132,161],"front":[115,157],"end":[116],"output":[118],"log-mel":[121],"filter":[122],"bank":[123,153],"energies":[124],"(LFBE)":[125],"L2":[127],"loss.":[128],"find":[130],"that":[131],"improves":[133],"word":[135],"error":[136],"by":[138],"10.7%":[139],"directly":[146],"initialized":[147],"with":[148],"beamformer":[150],"mel-filter":[152],"coefficients":[154],"end.":[158],"Finally,":[159],"combining":[160],"produces":[165],"WER":[167],"31%":[170],"baseline.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-02-07T00:00:00"}