{"id":"https://openalex.org/W2037564206","doi":"https://doi.org/10.1109/sped.2013.6682653","title":"Lightly supervised acoustic model training for imprecisely and asynchronously transcribed speech","display_name":"Lightly supervised acoustic model training for imprecisely and asynchronously transcribed speech","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2037564206","doi":"https://doi.org/10.1109/sped.2013.6682653","mag":"2037564206"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2013.6682653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2013.6682653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"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":false,"raw_author_name":"Peter Mihajlik","raw_affiliation_strings":["Dept. of Telecom. & Media Informatics, Budapest Univ. of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Telecom. & Media Informatics, Budapest Univ. of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005658324","display_name":"Andr\u00e1s Balog","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andras Balog","raw_affiliation_strings":["THINKTech Research Center, V\u00e1c, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"THINKTech Research Center, V\u00e1c, Hungary","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6864,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68362774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","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":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.803476095199585},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7753140330314636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7213914394378662},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.7075937390327454},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5231553316116333},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4905969202518463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48241910338401794},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44925057888031006},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4466802179813385},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4386095404624939},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4327906370162964},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4110533893108368},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3592078685760498},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08349475264549255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803476095199585},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7753140330314636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7213914394378662},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.7075937390327454},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5231553316116333},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4905969202518463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48241910338401794},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44925057888031006},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4466802179813385},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4386095404624939},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4327906370162964},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4110533893108368},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3592078685760498},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08349475264549255},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2013.6682653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2013.6682653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W23007503","https://openalex.org/W88081813","https://openalex.org/W851005513","https://openalex.org/W1517939602","https://openalex.org/W1543522032","https://openalex.org/W1580603233","https://openalex.org/W1631260214","https://openalex.org/W1988967026","https://openalex.org/W2032942114","https://openalex.org/W2046932483","https://openalex.org/W2117590177","https://openalex.org/W2121299803","https://openalex.org/W2140653524","https://openalex.org/W2143577772","https://openalex.org/W2158195707","https://openalex.org/W2164505566","https://openalex.org/W2171947673","https://openalex.org/W2397066715","https://openalex.org/W4285719527","https://openalex.org/W6600985776","https://openalex.org/W6630997582","https://openalex.org/W6632726156","https://openalex.org/W6636811518","https://openalex.org/W6677717300","https://openalex.org/W6712438494"],"related_works":["https://openalex.org/W3033638958","https://openalex.org/W7946549","https://openalex.org/W2374918184","https://openalex.org/W3011988934","https://openalex.org/W2917344756","https://openalex.org/W2161706778","https://openalex.org/W879197741","https://openalex.org/W2793122029","https://openalex.org/W2888383292","https://openalex.org/W2037564206"],"abstract_inverted_index":{"In":[0,59],"a":[1,7,75,111],"variety":[2],"of":[3,10,45,70,99],"speech":[4,102,131,150],"recognition":[5,98],"tasks":[6],"large":[8],"amount":[9],"approximate":[11],"transcription":[12,69,166],"is":[13,20,56,82,89,116,145,167],"available":[14],"for":[15,24],"the":[16,43,50,93,119,122,159,162,173],"audio":[17],"material,":[18],"but":[19],"not":[21,57],"directly":[22],"applicable":[23],"acoustic":[25,79,114,143],"model":[26,80,88,115,144],"training.":[27],"Whereas":[28],"roughly":[29],"time-synchronous":[30],"closed-captions":[31],"or":[32],"proper":[33],"audiobook":[34],"texts":[35],"are":[36,133],"already":[37],"used":[38,90],"in":[39,151],"lightly":[40,76],"supervised":[41,77],"techniques,":[42],"utilization":[44],"more":[46],"imperfect":[47],"and":[48,103,129,161],"at":[49,67],"same":[51],"time":[52],"completely":[53],"unaligned":[54,130],"transcriptions":[55,128],"self-evident.":[58],"this":[60],"paper":[61],"we":[62],"describe":[63],"our":[64],"experiments":[65],"aiming":[66],"automated":[68],"Hungarian":[71],"parliamentary":[72,100,123],"speeches.":[73],"Essentially,":[74],"across-domain":[78],"adaptation/retraining":[81],"performed.":[83],"A":[84],"low-resource":[85],"broadcast":[86],"news":[87],"to":[91,121,172],"bootstrap":[92],"process.":[94],"Relying":[95],"on":[96,104,147],"automatic":[97,160],"training":[101],"dynamic":[105],"text":[106],"alignment":[107],"based":[108],"data":[109,132],"selection,":[110],"new,":[112],"task-specific":[113],"built.":[117],"For":[118],"adaptation":[120],"domain,":[124],"only":[125,168],"edited":[126],"official":[127,165],"used,":[134],"without":[135],"any":[136],"additional":[137],"human":[138,163],"annotation":[139],"effort.":[140],"The":[141,154],"adapted":[142],"applied":[146],"unseen":[148],"target":[149],"real-time":[152],"recognition.":[153],"word":[155],"accuracy":[156],"difference":[157],"between":[158],"powered,":[164],"5%":[169],"(as":[170],"compared":[171],"exact":[174],"reference":[175],"text).":[176]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}