{"id":"https://openalex.org/W284676832","doi":"https://doi.org/10.21437/eurospeech.2001-160","title":"Efficient decoding strategy for conversational speech recognition using state-space models for vocal-tract-resonance dynamics","display_name":"Efficient decoding strategy for conversational speech recognition using state-space models for vocal-tract-resonance dynamics","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W284676832","doi":"https://doi.org/10.21437/eurospeech.2001-160","mag":"284676832"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-160","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5018625471","display_name":"Zaremba Jeff","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jeff Z. Ma","raw_affiliation_strings":["BBN Technologies ,"],"affiliations":[{"raw_affiliation_string":"BBN Technologies ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018625471"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6063,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66635688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"603","last_page":"606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9923999905586243,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9915000200271606,"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":0.764157772064209},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7467312216758728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.673105001449585},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6422593593597412},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.583821713924408},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.46367642283439636},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4246300756931305},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42244601249694824},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4195511043071747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3853434920310974},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34672683477401733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1312163770198822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764157772064209},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7467312216758728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.673105001449585},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6422593593597412},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.583821713924408},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.46367642283439636},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4246300756931305},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42244601249694824},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4195511043071747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3853434920310974},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34672683477401733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1312163770198822},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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:10.21437/eurospeech.2001-160","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1507322379","https://openalex.org/W2074812030","https://openalex.org/W2083393647","https://openalex.org/W2088112392","https://openalex.org/W2092684968","https://openalex.org/W2148812765","https://openalex.org/W2465919943","https://openalex.org/W2483982199","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5],"efficient":[6],"strategy":[7,74,139],"for":[8,23,43,63],"likelihood":[9],"computation":[10],"and":[11,104,158],"decoding":[12,95,138],"in":[13,34,86,112],"a":[14,35,72],"continuous":[15],"speech":[16,26,50,126],"recognizer":[17],"using":[18,118,127,163],"underlying":[19],"state-space":[20,29,65,160],"dynamic":[21,161],"models":[22,30,66],"the":[24,44,81,87,98,109,113,119,128,133,136,144,151,155,159,164],"hidden":[25],"dynamics.":[27],"The":[28,55],"have":[31],"been":[32],"constructed":[33],"special":[36],"way":[37],"so":[38],"as":[39],"to":[40,79],"be":[41],"suitable":[42],"conversational":[45,125],"or":[46],"casual":[47],"style":[48],"of":[49,83,135,142],"where":[51],"phonetic":[52,166],"reduction":[53],"abounds.":[54],"interacting":[56],"multiple":[57],"model":[58,162],"(IMM)":[59],"state":[60],"estimation":[61],"algorithm":[62],"switching":[64,88],"is":[67,140],"first":[68],"introduced,":[69],"which":[70],"uses":[71],"merging":[73,99],"derived":[75],"from":[76],"Bayes\u2019s":[77],"rule":[78],"meet":[80],"challenge":[82],"exponential":[84,110],"growth":[85,111],"combination.":[89],"Then":[90],"one":[91],"specific":[92],"dynamic-programming":[93],"based":[94],"algorithm,":[96],"incorporating":[97],"strategy,":[100],"are":[101],"derived,":[102],"implemented,":[103],"evaluated.":[105],"It":[106],"successfully":[107],"overcomes":[108],"original":[114],"search":[115],"paths":[116],"by":[117],"path-merging":[120],"strategy.":[121],"Evaluation":[122],"experiments":[123],"on":[124],"Switchboard":[129],"corpus":[130],"demonstrate":[131],"that":[132],"use":[134],"new":[137],"capable":[141],"reducing":[143],"recognizer\u2019s":[145],"word":[146],"error":[147],"rate":[148],"compared":[149],"with":[150],"baseline":[152],"recognizers,":[153],"including":[154],"HMM":[156],"system":[157],"HMM-produced":[165],"boundaries,":[167],"under":[168],"identical":[169],"test":[170],"conditions.":[171]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}