{"id":"https://openalex.org/W2158457922","doi":"https://doi.org/10.21437/interspeech.2005-135","title":"Speech trajectory clustering for improved speech recognition","display_name":"Speech trajectory clustering for improved speech recognition","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W2158457922","doi":"https://doi.org/10.21437/interspeech.2005-135","mag":"2158457922"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-135","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5100681256","display_name":"Yan Han","orcid":"https://orcid.org/0000-0001-9937-0981"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yan Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091615805","display_name":"Johan de Veth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johan de Veth","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112869933","display_name":"Louis Boves","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louis Boves","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100681256"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9134,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82378002,"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":"2985","last_page":"2988"},"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":0.9972000122070312,"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/T12031","display_name":"Speech and dialogue systems","score":0.9972000122070312,"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":0.7876075506210327},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7606103420257568},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7487172484397888},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6285171508789062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6058480143547058},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.601112961769104},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46939486265182495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43628543615341187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3933763802051544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876075506210327},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7606103420257568},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7487172484397888},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6285171508789062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6058480143547058},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.601112961769104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46939486265182495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43628543615341187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3933763802051544},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2005-135","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.62.319","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lands.let.kun.nl/literature/yanhan.2005.3.pdf","raw_type":"text"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/42030","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/42030","pdf_url":null,"source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article in monograph or in proceedings"},{"id":"pmh:ru:oai:repository.ubn.ru.nl:2066/42030","is_oa":false,"landing_page_url":"http://hdl.handle.net/2066/42030","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of Interspeech 2005 (IS2005), 2985 - 2988. Lisbon, Portugal : ISCA - CD-ROM","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W151018310","https://openalex.org/W1504344060","https://openalex.org/W2047216628","https://openalex.org/W2060526876","https://openalex.org/W2076104741","https://openalex.org/W2108840068","https://openalex.org/W2121464381","https://openalex.org/W2136528692","https://openalex.org/W2138324852","https://openalex.org/W2167200294"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Context":[0],"dependent":[1,171],"modelling":[2],"is":[3,25,48,123],"known":[4,38,59],"to":[5,79,132],"improve":[6],"recognition":[7,183],"performance":[8],"for":[9,33],"automatic":[10],"speech":[11,46,116,133],"recognition.":[12],"One":[13],"of":[14,19,55,83,115,118,146],"the":[15,27,31,42,45,61,68,81,111,127,161],"major":[16],"limitations,":[17],"especially":[18],"approaches":[20],"based":[21,124,141,151,169],"on":[22,67,125,142],"Decision":[23],"Trees,":[24],"that":[26,29,85,100,107,188],"questions":[28],"guide":[30],"search":[32],"effective":[34],"contexts":[35],"must":[36],"be":[37,58],"in":[39,44,176],"advance.":[40],"However,":[41],"variation":[43,84],"signals":[47],"caused":[49],"by":[50],"multiple":[51],"factors,":[52],"not":[53,77,102],"all":[54],"which":[56],"may":[57],"during":[60],"training":[62],"procedure.":[63],"State":[64],"tying":[65],"methods,":[66],"other":[69],"hand,":[70],"are":[71],"strictly":[72],"local,":[73],"and":[74,106,167,173],"therefore":[75],"do":[76],"allow":[78],"reap":[80],"benefits":[82],"spans":[86],"longer":[87],"length":[88],"units":[89,117],"such":[90],"as":[91],"syllables.":[92],"In":[93,156],"this":[94,157],"paper,":[95],"we":[96,136,159],"present":[97],"an":[98],"approach":[99],"does":[101],"require":[103],"prior":[104],"knowledge":[105,168],"still":[108],"can":[109],"find":[110],"most":[112],"important":[113],"variants":[114],"arbitrary":[119],"length.":[120],"The":[121],"method":[122],"clustering":[126],"multi-dimensional":[128],"dynamic":[129,147],"trajectories":[130,148],"corresponding":[131],"units.":[134],"Thus,":[135],"define":[137],"multipath":[138],"model":[139,179],"topologies":[140],"automatically":[143],"derived":[144],"clusters":[145,162],"(Trajectory":[149],"Clustering":[150,166],"hidden":[152],"Markov":[153],"models,":[154],"TCHMMs).":[155],"paper":[158],"compare":[160],"obtained":[163],"with":[164],"Trajectory":[165],"context":[170],"Head":[172],"Tail":[174],"models":[175,193],"a":[177],"Head-Body-Tail":[178],"(HBT)":[180],"connected":[181],"digits":[182],"task.":[184],"Our":[185],"results":[186],"show":[187],"TCHMMs":[189],"outperform":[190],"conventional":[191],"HBT":[192],"significantly.":[194]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}