{"id":"https://openalex.org/W3112480982","doi":"https://doi.org/10.1109/smc42975.2020.9283401","title":"Sub-word Based End-to-End Speech Recognition for an Under-Resourced Language: Amharic","display_name":"Sub-word Based End-to-End Speech Recognition for an Under-Resourced Language: Amharic","publication_year":2020,"publication_date":"2020-10-11","ids":{"openalex":"https://openalex.org/W3112480982","doi":"https://doi.org/10.1109/smc42975.2020.9283401","mag":"3112480982"},"language":"en","primary_location":{"id":"doi:10.1109/smc42975.2020.9283401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5007745889","display_name":"Nirayo Hailu Gebreegziabher","orcid":"https://orcid.org/0000-0001-5159-5241"},"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 Gebreegziabher","raw_affiliation_strings":["Faculty of Computer Science, Data and Knowledge Engineering Group, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Data and Knowledge Engineering Group, Otto-von-Guericke University of 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 of Magdeburg, Magdeburg, Germany"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Data and Knowledge Engineering Group, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007745889"],"corresponding_institution_ids":["https://openalex.org/I95793202"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56869053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"22","issue":null,"first_page":"3466","last_page":"3470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/amharic","display_name":"Amharic","score":0.9391164779663086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8382448554039001},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7469755411148071},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6602538824081421},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6366829872131348},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.607455313205719},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.574253261089325},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5497668981552124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5097091197967529},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.505850076675415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5005791187286377},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4776274561882019},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4460330605506897},{"id":"https://openalex.org/keywords/syllabification","display_name":"Syllabification","score":0.4337593913078308},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41416841745376587},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4093393087387085},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35746830701828003},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.35403844714164734},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31329789757728577},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08537185192108154},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.07995548844337463}],"concepts":[{"id":"https://openalex.org/C2780900699","wikidata":"https://www.wikidata.org/wiki/Q28244","display_name":"Amharic","level":2,"score":0.9391164779663086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382448554039001},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7469755411148071},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6602538824081421},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6366829872131348},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.607455313205719},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.574253261089325},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5497668981552124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5097091197967529},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.505850076675415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005791187286377},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4776274561882019},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4460330605506897},{"id":"https://openalex.org/C2779211743","wikidata":"https://www.wikidata.org/wiki/Q11994045","display_name":"Syllabification","level":3,"score":0.4337593913078308},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41416841745376587},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4093393087387085},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35746830701828003},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.35403844714164734},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31329789757728577},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08537185192108154},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.07995548844337463},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc42975.2020.9283401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2195354","https://openalex.org/W14941018","https://openalex.org/W854541894","https://openalex.org/W1836465849","https://openalex.org/W1995562189","https://openalex.org/W2012026885","https://openalex.org/W2034016314","https://openalex.org/W2094544353","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2521999726","https://openalex.org/W2530876040","https://openalex.org/W2620869433","https://openalex.org/W2805294584","https://openalex.org/W2808939837","https://openalex.org/W2962826786","https://openalex.org/W2976274203","https://openalex.org/W4246962055","https://openalex.org/W6600087822","https://openalex.org/W6623517193","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6687566353"],"related_works":["https://openalex.org/W2034016314","https://openalex.org/W3028477281","https://openalex.org/W2195354","https://openalex.org/W4311415364","https://openalex.org/W2157598242","https://openalex.org/W2612953387","https://openalex.org/W3151376046","https://openalex.org/W3089379469","https://openalex.org/W2903652364","https://openalex.org/W2147630093"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,51,139],"focused":[4],"on":[5,47,120],"end-to-end":[6,44,58,85,108,159],"speech":[7,45,86,109,126],"recognition":[8,46,87,110],"for":[9,82,112,156],"less-resourced":[10,48],"language,":[11],"Amharic.":[12],"The":[13,71,116],"result":[14,102],"can":[15,90],"be":[16,91],"integrated":[17],"with":[18,60],"other":[19],"tasks":[20],"such":[21],"as":[22,93],"spoken":[23],"content":[24],"retrieval.":[25],"We":[26,98],"explored":[27],"three":[28],"models,":[29],"which":[30,89],"consist":[31],"of":[32,55,124,146,154],"Convolutional":[33],"Neural":[34,37],"Networks,":[35,38],"Recurrent":[36],"and":[39,67,106,131,148,163],"Connectionist":[40],"Temporal":[41],"Classification,":[42],"towards":[43],"language.":[49,115],"Further,":[50],"studied":[52],"the":[53,64,83,100,136],"possibility":[54],"having":[56],"an":[57,94],"system":[59,88],"1-best":[61],"output":[62],"keeping":[63],"network":[65],"parameters":[66],"computational":[68],"resource":[69],"minimal.":[70],"paper":[72],"gives":[73],"attention":[74],"to":[75],"finding":[76],"a":[77,141,149,157],"more":[78],"suitable":[79],"sub-lexical":[80],"unit":[81],"Amharic":[84,125],"used":[92],"audio":[95],"indexing":[96],"unit.":[97],"present":[99],"first":[101],"comparing":[103],"grapheme,":[104],"phoneme,":[105],"syllable-based":[107,158],"systems":[111],"our":[113],"target":[114],"models":[117],"are":[118],"evaluated":[119],"approximately":[121],"52":[122],"hours":[123],"corpus":[127],"containing":[128],"read-speech,":[129],"audiobooks,":[130],"multi-genre":[132],"radio":[133],"programs.":[134],"On":[135],"test":[137],"set,":[138],"report":[140],"character":[142],"error":[143,151],"rate":[144,152],"(CER)":[145],"19.21%":[147],"syllable":[150],"(SER)":[153],"39.98%":[155],"model":[160,165],"without":[161],"lexicons":[162],"language":[164],"integrated.":[166]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}