{"id":"https://openalex.org/W2001387839","doi":"https://doi.org/10.1109/coginfocom.2012.6422008","title":"Thinking about the present and future of the complex speech recognition","display_name":"Thinking about the present and future of the complex speech recognition","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2001387839","doi":"https://doi.org/10.1109/coginfocom.2012.6422008","mag":"2001387839"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom.2012.6422008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2012.6422008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom)","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/A5088818569","display_name":"Kl\u00e1ra Vicsi","orcid":"https://orcid.org/0000-0002-7828-6833"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Klara Vicsi","raw_affiliation_strings":["Laboratory of Speech Acoustics of Department of Telecommunication and Mediainformatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Hungary","Laboratory of Speech Acoustics of Department of Telecommunication and Mediainformatics of Budapest University of Technology and Economics, Hungary"],"affiliations":[{"raw_affiliation_string":"Laboratory of Speech Acoustics of Department of Telecommunication and Mediainformatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Laboratory of Speech Acoustics of Department of Telecommunication and Mediainformatics of Budapest University of Technology and Economics, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088818569"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0786555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"371","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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":0.9975000023841858,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9926000237464905,"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":0.7117141485214233},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6741514205932617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6399338245391846},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.5480343699455261},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.5224263072013855},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5220355987548828},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4512847065925598},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.441322386264801},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.440592885017395},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4119041860103607},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3887016475200653},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.364014208316803},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12647908926010132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117141485214233},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6741514205932617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6399338245391846},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.5480343699455261},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.5224263072013855},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5220355987548828},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4512847065925598},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.441322386264801},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.440592885017395},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4119041860103607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3887016475200653},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.364014208316803},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12647908926010132},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coginfocom.2012.6422008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2012.6422008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W1524975733","https://openalex.org/W1575431606","https://openalex.org/W1586300189","https://openalex.org/W1590203237","https://openalex.org/W1597533204","https://openalex.org/W1608493013","https://openalex.org/W1877570817","https://openalex.org/W1972873790","https://openalex.org/W1990005915","https://openalex.org/W1997560282","https://openalex.org/W2001285045","https://openalex.org/W2003837801","https://openalex.org/W2021396747","https://openalex.org/W2024539680","https://openalex.org/W2074788634","https://openalex.org/W2118329604","https://openalex.org/W2124397839","https://openalex.org/W2125610823","https://openalex.org/W2134237567","https://openalex.org/W2158208761","https://openalex.org/W2158339352","https://openalex.org/W2296235715","https://openalex.org/W2401426213","https://openalex.org/W2614201817","https://openalex.org/W4285719527","https://openalex.org/W6605737493","https://openalex.org/W6635250320","https://openalex.org/W6635726886","https://openalex.org/W6636419984","https://openalex.org/W6697510278","https://openalex.org/W6737637619"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2355709873","https://openalex.org/W2619911963","https://openalex.org/W2389353568","https://openalex.org/W2184127972","https://openalex.org/W2105439218","https://openalex.org/W2964829415","https://openalex.org/W2355899496","https://openalex.org/W2001387839","https://openalex.org/W642007152"],"abstract_inverted_index":{"A":[0],"critical":[1],"point":[2],"of":[3,12,15,25,28,95,103],"the":[4,10,13,26,36,42,54,57,85,93,96,99],"most":[5],"cognitive":[6],"info-communication":[7],"systems":[8,40],"is":[9],"state":[11],"development":[14],"speech":[16,30,58,60,62],"recognition":[17,31],"technology.":[18],"The":[19],"paper":[20],"gives":[21],"a":[22,50],"short":[23],"introduction":[24],"principles":[27],"this":[29,75],"technology":[32],"today.":[33],"It":[34],"highlights":[35],"fact":[37],"that":[38],"these":[39],"in":[41,74,112],"market":[43],"are":[44,68,88,106],"only":[45,49],"speech-to-text":[46],"transformers":[47],"giving":[48],"word":[51],"chain":[52],"at":[53],"output,":[55],"where":[56],"prosody,":[59],"emotion,":[61],"style":[63],"and":[64],"more":[65],"other":[66],"information":[67],"not":[69],"involved.":[70],"Many":[71],"uncertainties":[72],"exist":[73],"operational":[76],"system.":[77],"Some":[78],"up":[79],"to":[80,91],"date":[81],"research":[82,101],"tendencies,":[83],"mostly":[84],"parallel":[86],"processing":[87],"introduced":[89,108],"aiming":[90],"increase":[92],"efficiencies":[94],"recognition.":[97],"At":[98],"end,":[100],"agenda":[102],"META":[104],"NET":[105],"shortly":[107],"for":[109],"Multilingual":[110],"Europe":[111],"2020.":[113]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
