{"id":"https://openalex.org/W3114977753","doi":"https://doi.org/10.1109/mmsp48831.2020.9287127","title":"Improving Automatic Speech Recognition Utilizing Audio-codecs for Data Augmentation","display_name":"Improving Automatic Speech Recognition Utilizing Audio-codecs for Data Augmentation","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3114977753","doi":"https://doi.org/10.1109/mmsp48831.2020.9287127","mag":"3114977753"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp48831.2020.9287127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","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/A5108209496","display_name":"Nirayo Hailu","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":true,"raw_author_name":"Nirayo Hailu","raw_affiliation_strings":["Faculty of Computer Science, Data and Knowledge Engineering Group, Otto-von-Guericke University Magdeburg, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Data and Knowledge Engineering Group, Otto-von-Guericke University Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033995312","display_name":"Ingo Siegert","orcid":"https://orcid.org/0000-0001-7447-7141"},"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":"Ingo Siegert","raw_affiliation_strings":["Faculty of Electrical Engineering and Information Technology, Mobile Dialog Systems Otto-von-Guericke University Magdeburg, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering and Information Technology, Mobile Dialog Systems Otto-von-Guericke University Magdeburg, 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 Nurnberger","raw_affiliation_strings":["Faculty of Computer Science, Data and Knowledge Engineering Group, Otto-von-Guericke University Magdeburg, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Data and Knowledge Engineering Group, Otto-von-Guericke University Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108209496"],"corresponding_institution_ids":["https://openalex.org/I95793202"],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73925122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9995999932289124,"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":0.9983999729156494,"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":0.8418648838996887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.737646222114563},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6918038725852966},{"id":"https://openalex.org/keywords/amharic","display_name":"Amharic","score":0.5507814884185791},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.500514030456543},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.4662075936794281},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.4637390375137329},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43013519048690796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4130710959434509},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3624758720397949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8418648838996887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.737646222114563},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6918038725852966},{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.5507814884185791},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.500514030456543},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.4662075936794281},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.4637390375137329},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43013519048690796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4130710959434509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3624758720397949},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp48831.2020.9287127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1502560247","https://openalex.org/W1836465849","https://openalex.org/W1885680957","https://openalex.org/W1970308149","https://openalex.org/W1990991587","https://openalex.org/W1995562189","https://openalex.org/W2016661008","https://openalex.org/W2095705004","https://openalex.org/W2099621636","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2396073756","https://openalex.org/W2407080277","https://openalex.org/W2510108135","https://openalex.org/W2521999726","https://openalex.org/W2530876040","https://openalex.org/W2557283755","https://openalex.org/W2591801237","https://openalex.org/W2756320212","https://openalex.org/W2776984718","https://openalex.org/W2902911519","https://openalex.org/W2936774411","https://openalex.org/W2962826786","https://openalex.org/W2964073500","https://openalex.org/W2964156885","https://openalex.org/W2976274203","https://openalex.org/W2983061588","https://openalex.org/W3030437843","https://openalex.org/W3215191595","https://openalex.org/W4205788663","https://openalex.org/W4252331534","https://openalex.org/W4252510720","https://openalex.org/W4301513688","https://openalex.org/W6630236247","https://openalex.org/W6630442970","https://openalex.org/W6638667902","https://openalex.org/W6639363673","https://openalex.org/W6674330103","https://openalex.org/W6687566353","https://openalex.org/W6713762819","https://openalex.org/W6730267373","https://openalex.org/W6734246609","https://openalex.org/W6747468998","https://openalex.org/W6771467084","https://openalex.org/W6803915641"],"related_works":["https://openalex.org/W2071761836","https://openalex.org/W2068668614","https://openalex.org/W3121919928","https://openalex.org/W1972048371","https://openalex.org/W584933867","https://openalex.org/W2021956231","https://openalex.org/W4386930358","https://openalex.org/W2114747788","https://openalex.org/W2061937230","https://openalex.org/W2132658536"],"abstract_inverted_index":{"To":[0,100],"train":[1],"end-to-end":[2,115],"automatic":[3,116],"speech":[4,14,117],"recognition":[5,118],"models,":[6],"it":[7,112],"requires":[8],"a":[9,137,177],"large":[10],"amount":[11],"of":[12,55,105,162,182],"labeled":[13],"data.":[15],"This":[16],"goal":[17],"is":[18,97,153],"challenging":[19],"for":[20,168],"languages":[21],"with":[22,60],"fewer":[23],"resources.":[24],"In":[25],"contrast":[26],"to":[27,37,155,185],"the":[28,39,48,74,80,91,102,106,125,128,142,156,172,186],"commonly":[29],"used":[30],"feature":[31,95],"level":[32],"data":[33,49,76],"augmentation,":[34],"we":[35,84,110,135,175],"propose":[36],"expand":[38],"training":[40],"set":[41],"by":[42],"using":[43,56],"different":[44,57],"audio":[45,58,81],"codecs":[46,59],"at":[47],"level.":[50],"The":[51,69,151],"augmentation":[52,108],"method":[53],"consists":[54],"changed":[61],"bit":[62,67],"rate,":[63,65],"sampling":[64],"and":[66,93,132,166],"depth.":[68],"change":[70],"reassures":[71],"variation":[72],"in":[73,113,120,141],"input":[75],"without":[77,147],"drastically":[78],"affecting":[79],"quality.":[82],"Besides,":[83],"can":[85],"ensure":[86],"that":[87],"humans":[88],"still":[89],"perceive":[90],"audio,":[92],"any":[94],"extraction":[96],"possible":[98],"later.":[99],"demonstrate":[101],"general":[103],"applicability":[104],"proposed":[107],"technique,":[109],"evaluated":[111],"an":[114],"architecture":[119],"four":[121],"languages.":[122],"After":[123],"applying":[124],"method,":[126],"on":[127],"Amharic,":[129],"Dutch,":[130],"Slovenian,":[131],"Turkish":[133],"datasets,":[134],"achieved":[136],"1.57":[138],"average":[139],"improvement":[140,161],"character":[143],"error":[144,179],"rates":[145],"(CER)":[146],"integrating":[148],"language":[149],"models.":[150],"result":[152],"comparable":[154],"baseline":[157,187],"result,":[158],"showing":[159],"CER":[160],"2.78,":[163],"1.25,":[164],"1.21,":[165],"1.05":[167],"each":[169],"language.":[170],"On":[171],"Amharic":[173],"dataset,":[174],"reached":[176],"syllable":[178],"rate":[180],"reduction":[181],"6.12":[183],"compared":[184],"result.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}