{"id":"https://openalex.org/W3204844985","doi":"https://doi.org/10.1109/asru51503.2021.9688123","title":"On Architectures and Training for Raw Waveform Feature Extraction in ASR","display_name":"On Architectures and Training for Raw Waveform Feature Extraction in ASR","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3204844985","doi":"https://doi.org/10.1109/asru51503.2021.9688123","mag":"3204844985"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688123","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.04298","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055945494","display_name":"Peter Vieting","orcid":"https://orcid.org/0000-0002-3582-5382"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Peter Vieting","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060461441","display_name":"Christoph L\u00fcscher","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Luscher","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029547617","display_name":"Wilfried Michel","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wilfried Michel","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055945494"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.1269,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35505037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"267","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.8232572078704834},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6605663299560547},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6096845865249634},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5750283002853394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5523470640182495},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.552026093006134},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5437553524971008},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5415078401565552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210475325584412},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5146639943122864},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4557603597640991},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.452237069606781},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.41063281893730164},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1824587881565094},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09135591983795166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8232572078704834},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6605663299560547},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6096845865249634},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5750283002853394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5523470640182495},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.552026093006134},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5437553524971008},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5415078401565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210475325584412},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5146639943122864},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4557603597640991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.452237069606781},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.41063281893730164},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1824587881565094},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09135591983795166},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9688123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688123","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.04298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.04298","pdf_url":"https://arxiv.org/pdf/2104.04298","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":"","raw_type":"text"},{"id":"mag:3204844985","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.04298.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2104.04298","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.04298","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.04298","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.04298","pdf_url":"https://arxiv.org/pdf/2104.04298","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1273438319","display_name":null,"funder_award_id":"694537","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3204844985.pdf","grobid_xml":"https://content.openalex.org/works/W3204844985.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1573166544","https://openalex.org/W1828163288","https://openalex.org/W2009150118","https://openalex.org/W2024200390","https://openalex.org/W2037976268","https://openalex.org/W2168249605","https://openalex.org/W2327501763","https://openalex.org/W2398826216","https://openalex.org/W2401869809","https://openalex.org/W2408093180","https://openalex.org/W2799923439","https://openalex.org/W2799958557","https://openalex.org/W2900440209","https://openalex.org/W2905489173","https://openalex.org/W2916979304","https://openalex.org/W2939690918","https://openalex.org/W2943845043","https://openalex.org/W2944255943","https://openalex.org/W2962728618","https://openalex.org/W2964052309","https://openalex.org/W2972692349","https://openalex.org/W2973049979","https://openalex.org/W2996383576","https://openalex.org/W3003382064","https://openalex.org/W3015411292","https://openalex.org/W3015726069","https://openalex.org/W3016234571","https://openalex.org/W3025165719","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3097558625","https://openalex.org/W3099782249","https://openalex.org/W3102342027","https://openalex.org/W3103005696","https://openalex.org/W3132613748","https://openalex.org/W3160551958","https://openalex.org/W4238620777","https://openalex.org/W6638749077","https://openalex.org/W6684821101","https://openalex.org/W6723481938","https://openalex.org/W6750824539","https://openalex.org/W6757717501","https://openalex.org/W6764260666","https://openalex.org/W6765658108","https://openalex.org/W6769196770","https://openalex.org/W6777337586","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6785097957"],"related_works":["https://openalex.org/W3155168732","https://openalex.org/W2913566369","https://openalex.org/W1974455634","https://openalex.org/W590458053","https://openalex.org/W3211655143","https://openalex.org/W2992448548","https://openalex.org/W3211228299","https://openalex.org/W2760599032","https://openalex.org/W2962995362","https://openalex.org/W3155343771","https://openalex.org/W3094225009","https://openalex.org/W2790326622","https://openalex.org/W3168285598","https://openalex.org/W2586425531","https://openalex.org/W2488933957","https://openalex.org/W2890351244","https://openalex.org/W2915067382","https://openalex.org/W3087644184","https://openalex.org/W2963701934","https://openalex.org/W154005992"],"abstract_inverted_index":{"With":[0],"the":[1,26,55,82,98,109,113,137,145],"success":[2],"of":[3,20,32,39,57,59,97,101,111,136],"neural":[4],"network":[5],"based":[6,24],"modeling":[7,17],"in":[8,65,140],"auto-matic":[9],"speech":[10],"recognition":[11],"(ASR),":[12],"many":[13],"studies":[14],"investigated":[15],"acoustic":[16,99,125],"and":[18,117],"learning":[19],"feature":[21,40,87,115],"extractors":[22,41],"directly":[23],"on":[25,36,42],"raw":[27],"waveform.":[28],"Recently,":[29],"one":[30,58],"line":[31],"research":[33],"has":[34],"focused":[35],"unsupervised":[37],"pre-training":[38],"audio-only":[43],"data":[44,71],"to":[45,81,92,120,142],"improve":[46],"downstream":[47],"ASR":[48,74,103],"performance.":[49,146],"In":[50],"this":[51,78],"work,":[52],"we":[53,132],"investigate":[54],"usefulness":[56],"these":[60],"front-end":[61],"frameworks,":[62],"namely":[63],"wav2vec,":[64],"a":[66],"setting":[67],"without":[68],"additional":[69],"untranscribed":[70],"for":[72],"hybrid":[73],"systems.":[75],"We":[76,107],"compare":[77],"framework":[79],"both":[80],"manually":[83],"defined":[84],"stan-dard":[85],"Gammatone":[86],"set,":[88],"as":[89,91,95],"well":[90],"features":[93,139],"extracted":[94],"part":[96],"model":[100,126],"an":[102,123],"system":[104],"trained":[105,127],"su-pervised.":[106],"study":[108],"benefits":[110],"using":[112],"pre-trained":[114],"extractor":[116],"explore":[118],"how":[119],"additionally":[121],"exploit":[122],"ex-isting":[124],"with":[128],"different":[129],"features.":[130],"Finally,":[131],"systematically":[133],"examine":[134],"combinations":[135],"described":[138],"order":[141],"further":[143],"advance":[144]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}