{"id":"https://openalex.org/W116006226","doi":"https://doi.org/10.21437/eurospeech.1999-531x","title":"A public domain speech-to-text system","display_name":"A public domain speech-to-text system","publication_year":1999,"publication_date":"1999-09-05","ids":{"openalex":"https://openalex.org/W116006226","doi":"https://doi.org/10.21437/eurospeech.1999-531x","mag":"116006226"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1999-531x","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-531x","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","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/A5056342308","display_name":"M. Ordowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Ordowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079186826","display_name":"N. Deshmukh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N. Deshmukh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027786016","display_name":"A. Ganapathiraju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Ganapathiraju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110156490","display_name":"J. Hamaker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Hamaker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004343613","display_name":"J. Picone","orcid":"https://orcid.org/0000-0001-6836-7886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Picone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0829,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.87419547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2127","last_page":"2130"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9954000115394592,"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":0.7822327613830566},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.725434422492981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6535223722457886},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5990140438079834},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5916446447372437},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.584703803062439},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5783249139785767},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5713032484054565},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5303533673286438},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5196115374565125},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5128427147865295},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4633181095123291},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45288729667663574},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44914016127586365},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4340936839580536},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.42332810163497925},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4166482985019684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4046016335487366},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.26807230710983276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11541363596916199},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11285018920898438},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09980577230453491},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07530659437179565}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822327613830566},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.725434422492981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6535223722457886},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5990140438079834},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5916446447372437},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.584703803062439},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5783249139785767},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5713032484054565},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5303533673286438},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5196115374565125},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5128427147865295},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4633181095123291},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45288729667663574},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44914016127586365},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4340936839580536},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.42332810163497925},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4166482985019684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4046016335487366},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.26807230710983276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11541363596916199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11285018920898438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09980577230453491},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07530659437179565},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1999-531x","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-531x","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.3722","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.3722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.msstate.edu/research/isip/publications/conferences/eurospeech/1999/decoder/paper_v4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W27187656","https://openalex.org/W1501633760","https://openalex.org/W1996903695","https://openalex.org/W2002089154","https://openalex.org/W2081323593","https://openalex.org/W2166637769"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2164147372","https://openalex.org/W4253660971","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2550171623","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"The":[0,23],"lack":[1],"of":[2,17,26,56,73,99,117],"freely":[3],"available":[4,58],"state-of-the-art":[5,32,59],"Speech-to-Text":[6],"(STT)":[7],"software":[8],"has":[9],"been":[10],"a":[11,71,76,84,88,97,104,115],"major":[12],"hindrance":[13],"to":[14,30],"the":[15,27,53,67,81,93,109],"development":[16],"new":[18,43],"audio":[19],"information":[20],"processing":[21],"technology.":[22],"high":[24],"cost":[25],"infrastructure":[28],"required":[29],"conduct":[31],"speech":[33,68],"recognition":[34],"research":[35,39],"prevents":[36],"many":[37],"small":[38],"groups":[40],"from":[41],"evaluating":[42],"ideas":[44],"on":[45],"large-scale":[46],"tasks.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"present":[52],"core":[54],"components":[55],"an":[57,62],"STT":[60],"system:":[61],"acoustic":[63],"processor":[64,90],"which":[65,79,91,107],"converts":[66],"signal":[69],"into":[70],"sequence":[72,98,113],"feature":[74,118],"vectors;":[75],"training":[77],"module":[78],"estimates":[80],"parameters":[82],"for":[83],"Hidden":[85],"Markov":[86],"Model;":[87],"linguistic":[89],"predicts":[92],"next":[94],"word":[95,112],"given":[96,114],"previously":[100],"recognized":[101],"words;":[102],"and":[103],"search":[105],"engine":[106],"finds":[108],"most":[110],"probable":[111],"set":[116],"vectors.":[119],"1.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}