{"id":"https://openalex.org/W175164482","doi":"https://doi.org/10.21437/eurospeech.1997-23","title":"Segmentation and modeling in segment-based recognition","display_name":"Segmentation and modeling in segment-based recognition","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W175164482","doi":"https://doi.org/10.21437/eurospeech.1997-23","mag":"175164482"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5113710816","display_name":"Jane W. Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jane W. Chang","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James R. Glass","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113710816"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":5.4339,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95368947,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1199","last_page":"1202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.8068122267723083},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6615337133407593},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6494014263153076},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.585261344909668},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5738381743431091},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.549135148525238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5296235680580139},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5213221907615662},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4991312026977539},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4945981204509735},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4944193363189697},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4675758183002472},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.43803641200065613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3632815182209015},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.284399151802063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068122267723083},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6615337133407593},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6494014263153076},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.585261344909668},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5738381743431091},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.549135148525238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296235680580139},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5213221907615662},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4991312026977539},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4945981204509735},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4944193363189697},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4675758183002472},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.43803641200065613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3632815182209015},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.284399151802063},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.1997-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.200.2211","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.200.2211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.csail.mit.edu/sls/publications/1997/eurospeech97-jwc.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.558.9111","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.558.9111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/jrg/1997/eurospeech97-chang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W186915233","https://openalex.org/W1802969839","https://openalex.org/W1877154798","https://openalex.org/W2087863531","https://openalex.org/W2405839257","https://openalex.org/W2584852661"],"related_works":["https://openalex.org/W2377402383","https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W2050397613","https://openalex.org/W2080458333","https://openalex.org/W1995562189","https://openalex.org/W172689163","https://openalex.org/W1507177964","https://openalex.org/W2611200336"],"abstract_inverted_index":{"Recently,":[0],"we":[1,39,77,86,114,154],"have":[2],"developed":[3],"a":[4,17,62,97,123,140,156,174],"probabilistic":[5,98],"framework":[6,117],"for":[7,46,68],"segment-based":[8],"speech":[9,14],"recognition":[10,147],"that":[11,41,60,70,100,126],"represents":[12],"the":[13,32,51,109,149,164],"signal":[15],"as":[16],"network":[18,33],"of":[19,161],"segments":[20,69,138],"and":[21,121],"associated":[22],"feature":[23,48],"vectors":[24,49],"[2].":[25],"Although":[26],"in":[27,50,139,145,152,178],"general,":[28],"each":[29,42],"path":[30,43],"through":[31],"does":[34],"not":[35,72],"traverse":[36],"all":[37,47,137],"segments,":[38],"ar-gued":[40],"must":[44],"account":[45,67],"network.":[52,141],"We":[53,142],"then":[54],"demonstrated":[55],"an":[56],"efficient":[57],"search":[58,124],"algorithm":[59,91,99,125],"uses":[61],"single":[63],"additional":[64],"model":[65],"to":[66,82,118,132],"are":[71],"traversed.":[73],"In":[74],"this":[75],"paper,":[76],"present":[78],"two":[79],"new":[80],"extensions":[81],"our":[83,88,116,182],"framework.":[84],"First,":[85],"replace":[87],"acoustic":[89],"segmentation":[90],"with":[92],"\u201csegmentation":[93],"by":[94],"recognition,":[95],"\u201d":[96],"can":[101,127],"combine":[102],"multiple":[103,130],"contextual":[104,134],"constraints":[105,135],"towards":[106],"hypothesizing":[107],"only":[108],"most":[110],"likely":[111],"seg-ments.":[112],"Second,":[113],"generalize":[115],"\u201cnear-miss":[119],"modeling\u201d":[120],"describe":[122],"efficiently":[128],"use":[129],"mod-els":[131],"enforce":[133],"across":[136],"report":[143],"experiments":[144],"phonetic":[146],"on":[148,163],"TIMIT":[150],"corpus":[151],"which":[153],"achieve":[155],"diphone":[157],"context-dependent":[158],"error":[159,179],"rate":[160,180],"26.6%":[162],"NIST":[165],"core":[166],"test":[167],"set":[168],"over":[169],"39":[170],"classes.":[171],"This":[172],"is":[173],"12.8":[175],"%":[176],"reduction":[177],"from":[181],"best":[183],"previously":[184],"reported":[185],"result.":[186],"1.":[187]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}