{"id":"https://openalex.org/W2099098972","doi":"https://doi.org/10.1109/icassp.1987.1169700","title":"A stochastic segment model for phoneme-based continuous speech recognition","display_name":"A stochastic segment model for phoneme-based continuous speech recognition","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W2099098972","doi":"https://doi.org/10.1109/icassp.1987.1169700","mag":"2099098972"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1987.1169700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5006694769","display_name":"S. Roucos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Roucos","raw_affiliation_strings":["BBN Laboratories, Inc., Cambridge, MA, USA","BBN Laboratories Incorporated, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Laboratories, Inc., Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Laboratories Incorporated, Cambridge, MA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071608365","display_name":"M. Dunham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Dunham","raw_affiliation_strings":["BBN Laboratories, Inc., Cambridge, MA, USA","BBN Laboratories Incorporated, Cambridge, MA 02238"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Laboratories, Inc., Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Laboratories Incorporated, Cambridge, MA 02238","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2465,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.52052416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"73","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9933000206947327,"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":0.9868999719619751,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7717329263687134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.700539767742157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6980710029602051},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6446946859359741},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4558698832988739},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44929730892181396},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.44491732120513916},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.43945956230163574},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4389653205871582},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43580350279808044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4292267858982086},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32662224769592285},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3207841217517853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22620120644569397}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7717329263687134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.700539767742157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980710029602051},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6446946859359741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4558698832988739},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44929730892181396},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.44491732120513916},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.43945956230163574},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4389653205871582},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43580350279808044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4292267858982086},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32662224769592285},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3207841217517853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22620120644569397},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1987.1169700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1987.1169700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1520663776","https://openalex.org/W1826405859","https://openalex.org/W1884313731","https://openalex.org/W1920769845","https://openalex.org/W1945490744","https://openalex.org/W1966812932","https://openalex.org/W2112197391","https://openalex.org/W2112372344","https://openalex.org/W2147039250","https://openalex.org/W2170585560"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698","https://openalex.org/W3009759344","https://openalex.org/W263057764","https://openalex.org/W2157504884"],"abstract_inverted_index":{"Developing":[0],"accurate":[1],"and":[2,68,101],"robust":[3],"phonetic":[4,38,133],"models":[5,109],"for":[6,15,34,106],"the":[7,30,55,75,78,94,98,102,118,122],"different":[8],"speech":[9,19,116],"sounds":[10],"is":[11,86],"a":[12,26,36,60,65,70,130],"major":[13],"challenge":[14],"high":[16],"performance":[17],"continuous":[18,111,115],"recognition.":[20],"In":[21,89],"this":[22,84,90],"paper,":[23,91],"we":[24,92],"introduce":[25],"new":[27],"approach,":[28],"called":[29,64],"stochastic":[31,48,95],"segment":[32,39,49,57,62,80,96,108,119],"model,":[33,97],"modelling":[35],"variable-length":[37,56],"X,":[40],"an":[41],"L-long":[42],"sequence":[43],"of":[44,52,74,77],"feature":[45],"vectors.":[46],"The":[47],"model":[50,120],"consists":[51],"1)":[53],"time-warping":[54],"X":[58],"into":[59],"fixed-length":[61],"Y":[63],"resampled":[66,79],"segment,":[67],"2)":[69],"joint":[71],"density":[72],"function":[73],"parameters":[76],"Y,":[81],"which":[82],"in":[83],"work":[85],"assumed":[87],"Gaussian.":[88],"describe":[93],"recognition":[99],"algorithm,":[100],"iterative":[103],"training":[104],"algorithm":[105],"estimating":[107],"from":[110],"speech.":[112],"For":[113],"speaker-dependent":[114],"recognition,":[117],"reduces":[121],"word":[123],"error":[124],"rate":[125],"by":[126],"one":[127],"third":[128],"over":[129],"hidden":[131],"Markov":[132],"model.":[134]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}