{"id":"https://openalex.org/W2170142019","doi":"https://doi.org/10.1109/icassp.1991.150332","title":"A variable duration acoustic segment HMM for hard-to-recognize words and phrases","display_name":"A variable duration acoustic segment HMM for hard-to-recognize words and phrases","publication_year":1991,"publication_date":"1991-01-01","ids":{"openalex":"https://openalex.org/W2170142019","doi":"https://doi.org/10.1109/icassp.1991.150332","mag":"2170142019"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1991.150332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1991.150332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"[Proceedings] ICASSP 91: 1991 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/A5111865087","display_name":"J.N. Marcus","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":false,"raw_author_name":"J.N. Marcus","raw_affiliation_strings":["Spoken Language Systems Group Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Group Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109575396","display_name":"Victor W. Zue","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":false,"raw_author_name":"V.W. Zue","raw_affiliation_strings":["Spoken Language Systems Group Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Group Laboratory of Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.794,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7333865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"284 vol. 1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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":0.9894000291824341,"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":0.8947526812553406},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8572648763656616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060667276382446},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6706953048706055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6386308670043945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6305834054946899},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5743481516838074},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5618807077407837},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5358515977859497},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5024936199188232},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.500009298324585},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4215043783187866},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17009928822517395},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14981088042259216},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06463751196861267}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8947526812553406},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8572648763656616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060667276382446},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6706953048706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6386308670043945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6305834054946899},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5743481516838074},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5618807077407837},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5358515977859497},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5024936199188232},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.500009298324585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4215043783187866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17009928822517395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14981088042259216},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06463751196861267},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1991.150332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1991.150332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"[Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W104015672","https://openalex.org/W162417025","https://openalex.org/W1538748823","https://openalex.org/W1610605641","https://openalex.org/W1863218161","https://openalex.org/W1906970275","https://openalex.org/W1920769845","https://openalex.org/W1974540032","https://openalex.org/W2030909238","https://openalex.org/W2084134149","https://openalex.org/W2584852661","https://openalex.org/W4233845624","https://openalex.org/W6604233312","https://openalex.org/W6606549138"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W3184921334","https://openalex.org/W4255446307","https://openalex.org/W2033009170","https://openalex.org/W4386895402","https://openalex.org/W3202382261","https://openalex.org/W2028814537","https://openalex.org/W2802807316"],"abstract_inverted_index":{"The":[0,29,78],"authors":[1,55],"consider":[2],"how":[3,17,57],"hidden":[4],"Markov":[5],"models":[6,21],"(HMM)":[7],"can":[8,22,72],"be":[9,23,73],"modified":[10],"to":[11,25,41],"accommodate":[12],"a":[13,37],"segment-based":[14],"representation,":[15],"and":[16,19,45],"word":[18],"subword":[20],"combined":[24],"improve":[26],"recognition":[27],"performance.":[28],"investigation":[30],"is":[31,81],"conducted":[32],"within":[33],"the":[34,48,54,69],"context":[35],"of":[36,59],"system":[38,80],"that":[39,65],"attempts":[40],"spot":[42],"confusable":[43],"words":[44],"phrases":[46],"in":[47,84],"VOYAGER":[49],"continuous":[50],"speech":[51],"corpus.":[52],"Specifically,":[53],"describe":[56],"segments":[58],"varying":[60],"duration":[61],"are":[62],"determined":[63],"such":[64],"measurements":[66],"for":[67],"estimating":[68],"model":[70],"parameters":[71],"made":[74],"on":[75],"these":[76],"segments.":[77],"word-spotting":[79],"also":[82],"described":[83],"detail.>":[85]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}