{"id":"https://openalex.org/W3127899948","doi":"https://doi.org/10.1145/3443279.3443313","title":"German Speech Recognition System using DeepSpeech","display_name":"German Speech Recognition System using DeepSpeech","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3127899948","doi":"https://doi.org/10.1145/3443279.3443313","mag":"3127899948"},"language":"en","primary_location":{"id":"doi:10.1145/3443279.3443313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"},"type":"article","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/A5079474815","display_name":"Jiahua Xu","orcid":"https://orcid.org/0000-0003-3672-373X"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke University Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jiahua Xu","raw_affiliation_strings":["Otto-von-Guericke University, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke University, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053989026","display_name":"Kaveen Matta","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke University Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kaveen Matta","raw_affiliation_strings":["Otto-von-Guericke University, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke University, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074901844","display_name":"Shaiful Islam","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke University Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shaiful Islam","raw_affiliation_strings":["Otto-von-Guericke University, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke University, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075663234","display_name":"Andreas N\u00fcrnberger","orcid":"https://orcid.org/0000-0003-4311-0624"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke University Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas N\u00fcrnberger","raw_affiliation_strings":["Otto-von-Guericke University, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Otto-von-Guericke University, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079474815"],"corresponding_institution_ids":["https://openalex.org/I95793202"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84123716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/T12031","display_name":"Speech and dialogue systems","score":0.9873999953269958,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.9268772602081299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8394140005111694},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7137637138366699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6291842460632324},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5909258127212524},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5650962591171265},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.555342435836792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112261772155762},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49407556653022766},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4256565272808075},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3381027579307556},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3073164224624634},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1550830900669098}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.9268772602081299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394140005111694},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7137637138366699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6291842460632324},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5909258127212524},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5650962591171265},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.555342435836792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112261772155762},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49407556653022766},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4256565272808075},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3381027579307556},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3073164224624634},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1550830900669098},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3443279.3443313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3443279.3443313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2406504561","https://openalex.org/W2962824709"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2126322296","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4386590854","https://openalex.org/W2620660273","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Speech":[0],"recognition":[1],"focus":[2],"on":[3,50,71],"the":[4,20,27,72,76,125,128,132],"translation":[5],"of":[6,29,57,127],"speech":[7],"from":[8],"an":[9],"audio":[10],"format":[11],"to":[12,99,107,123],"a":[13,80],"text.":[14],"Popular":[15],"models":[16,36],"are":[17,40],"available":[18],"for":[19,78,90,131],"English":[21],"language":[22,34,53],"as":[23],"open":[24,35],"source":[25],"in":[26],"domain":[28],"voice/speech":[30],"recognition;":[31],"however,":[32],"German":[33,46,52,69,82,116,133],"and":[37,60,74],"training":[38,79],"schemes":[39],"rather":[41],"rare.":[42],"An":[43],"end-to-end":[44],"real-time":[45,81],"speech-to-text":[47,83],"system":[48],"based":[49],"multiple":[51,68],"datasets":[54,70],"is":[55,87],"worthy":[56],"more":[58],"attention":[59],"further":[61],"investigation.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,103],"combined":[67],"market":[73],"optimizes":[75],"Deep-speech":[77],"model.":[84],"A":[85],"GUI":[86],"also":[88],"proposed":[89],"functionality":[91],"demonstration.":[92],"Our":[93],"model":[94,117,130],"performs":[95],"considerably":[96],"well":[97],"compared":[98],"other":[100],"state-of-the-art":[101],"since":[102],"utilized":[104],"noisy":[105],"data":[106],"replicate":[108],"real-life":[109],"scenarios.":[110],"We":[111],"released":[112],"our":[113],"fully":[114],"trained":[115],"along":[118],"with":[119],"its":[120],"parameter":[121],"configurations":[122],"promote":[124],"diversification":[126],"open-source":[129],"language.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
