{"id":"https://openalex.org/W2996353927","doi":"https://doi.org/10.1109/icassp40776.2020.9053008","title":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","display_name":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2996353927","doi":"https://doi.org/10.1109/icassp40776.2020.9053008","mag":"2996353927"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053008","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.09257","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063680910","display_name":"Nick Rossenbach","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":true,"raw_author_name":"Nick Rossenbach","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany","RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059521407","display_name":"Albert Zeyer","orcid":"https://orcid.org/0000-0002-6655-671X"},"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":"Albert Zeyer","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany","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":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany","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":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063680910"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.14685955,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50719745,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7069","last_page":"7073"},"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.7724830508232117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7393796443939209},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7199563980102539},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6378894448280334},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5320855975151062},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41612452268600464},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3409644365310669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724830508232117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7393796443939209},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7199563980102539},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6378894448280334},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5320855975151062},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41612452268600464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3409644365310669},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053008","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:1912.09257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.09257","pdf_url":"https://arxiv.org/pdf/1912.09257","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2996353927","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1912.09257","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.1912.09257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.09257","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"},{"id":"doi:10.17023/d65m-jr51","is_oa":true,"landing_page_url":"https://doi.org/10.17023/d65m-jr51","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"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:1912.09257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.09257","pdf_url":"https://arxiv.org/pdf/1912.09257","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5600000023841858,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2996353927.pdf","grobid_xml":"https://content.openalex.org/works/W2996353927.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2170212447","https://openalex.org/W2407080277","https://openalex.org/W2766812927","https://openalex.org/W2799800213","https://openalex.org/W2883586237","https://openalex.org/W2898727538","https://openalex.org/W2902786662","https://openalex.org/W2912937645","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2944255943","https://openalex.org/W2951516458","https://openalex.org/W2962699523","https://openalex.org/W2962728618","https://openalex.org/W2962784628","https://openalex.org/W2963272440","https://openalex.org/W2963581463","https://openalex.org/W2963609956","https://openalex.org/W2963796886","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972692349","https://openalex.org/W2972889948","https://openalex.org/W3103005696","https://openalex.org/W6623517193","https://openalex.org/W6713762819","https://openalex.org/W6745697700","https://openalex.org/W6746700228","https://openalex.org/W6750489868","https://openalex.org/W6756236667","https://openalex.org/W6756385397","https://openalex.org/W6903921188"],"related_works":["https://openalex.org/W3015449694","https://openalex.org/W3107298252","https://openalex.org/W3093147193","https://openalex.org/W2945078028","https://openalex.org/W3198047825","https://openalex.org/W2943008652","https://openalex.org/W3047866127","https://openalex.org/W3096246310","https://openalex.org/W3093346109","https://openalex.org/W3136258522","https://openalex.org/W3105804405","https://openalex.org/W2972818416","https://openalex.org/W2898727538","https://openalex.org/W2963739817","https://openalex.org/W2111482576","https://openalex.org/W3008749227","https://openalex.org/W3038127439","https://openalex.org/W3156915121","https://openalex.org/W2809035663","https://openalex.org/W3096615836"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,105,114],"text-to-speech":[3],"(TTS)":[4],"led":[5],"to":[6,46,54,102,122,137],"the":[7,35,61,77,120],"development":[8],"of":[9,63,76,100,135],"flexible":[10],"multi-speaker":[11],"end-to-end":[12,57],"TTS":[13,30,41],"systems.":[14],"We":[15,68,97,131],"extend":[16],"state-of-the-art":[17],"attention-based":[18],"automatic":[19],"speech":[20],"recognition":[21],"(ASR)":[22],"systems":[23,42,59],"with":[24,72,82,112],"synthetic":[25],"audio":[26],"generated":[27],"by":[28,127],"a":[29,109,115,123],"system":[31],"trained":[32],"only":[33],"on":[34,147],"ASR":[36,39,58,145],"corpora":[37],"itself.":[38],"and":[40,81,89],"are":[43,94],"built":[44],"separately":[45],"show":[47,90,133],"that":[48,91],"text-only":[49],"data":[50,80,84],"can":[51],"be":[52],"used":[53],"enhance":[55],"existing":[56],"without":[60],"necessity":[62],"parameter":[64],"or":[65],"architecture":[66],"changes.":[67],"compare":[69],"our":[70,142],"method":[71],"language":[73],"model":[74],"integration":[75],"same":[78],"text":[79],"simple":[83],"augmentation":[85],"methods":[86],"like":[87],"SpecAugment":[88],"performance":[92],"improvements":[93,99,134],"mostly":[95],"independent.":[96],"achieve":[98],"up":[101,136],"33%":[103],"relative":[104,139],"word-error-rate":[106],"(WER)":[107],"over":[108,141],"strong":[110],"baseline":[111,146],"data-augmentation":[113],"low-resource":[116],"environment":[117],"(LibriSpeech-100h),":[118],"closing":[119],"gap":[121],"comparable":[124],"oracle":[125],"experiment":[126],"more":[128],"than":[129],"50\\%.":[130],"also":[132],"5%":[138],"WER":[140],"most":[143],"recent":[144],"LibriSpeech-960h.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}