{"id":"https://openalex.org/W109008040","doi":"https://doi.org/10.21437/interspeech.2004-215","title":"A theoretical analysis of speech recognition based on feature trajectory models","display_name":"A theoretical analysis of speech recognition based on feature trajectory models","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W109008040","doi":"https://doi.org/10.21437/interspeech.2004-215","mag":"109008040"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-215","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5008413640","display_name":"Yasuhiro Minami","orcid":"https://orcid.org/0000-0003-3514-4285"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yasuhiro Minami","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik McDermott","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018620798","display_name":"Atsushi Nakamura","orcid":"https://orcid.org/0000-0003-0788-2221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsushi Nakamura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shigeru Katagiri","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008413640"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2485,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88532692,"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":"549","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9979000091552734,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9979000091552734,"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":0.9970999956130981,"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":0.9950000047683716,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8684742450714111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7203984260559082},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.719589352607727},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.709585428237915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6814639568328857},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6008241176605225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45393383502960205},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4513208568096161},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4496132731437683},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3157963752746582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.174216628074646}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8684742450714111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203984260559082},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.719589352607727},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.709585428237915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6814639568328857},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6008241176605225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45393383502960205},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4513208568096161},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4496132731437683},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3157963752746582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.174216628074646},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-215","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1584341804","https://openalex.org/W1853111913","https://openalex.org/W1935012542","https://openalex.org/W2020335243","https://openalex.org/W2081309747","https://openalex.org/W2118825896","https://openalex.org/W2125107595","https://openalex.org/W2159501365","https://openalex.org/W2169135280","https://openalex.org/W2465919943","https://openalex.org/W3036802551"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2084326697","https://openalex.org/W2194396582","https://openalex.org/W2027903142","https://openalex.org/W2082284720","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2354322608","https://openalex.org/W2379938888"],"abstract_inverted_index":{"In":[0],"previous":[1],"work,":[2],"we":[3],"proposed":[4],"a":[5,12,39,59,68],"new":[6],"speech":[7,14,34,82],"recognition":[8,83],"technique":[9],"that":[10,28,47,65],"generates":[11],"smooth":[13],"trajectory":[15,55],"from":[16],"hidden":[17],"Markov":[18],"models":[19],"(HMMs)":[20],"by":[21],"maximizing":[22],"likelihood":[23],"subject":[24],"to":[25,51,58],"the":[26,48,53,72],"constraints":[27],"exist":[29],"between":[30,71],"static":[31],"and":[32,84],"dynamic":[33],"features.":[35],"This":[36,62],"paper":[37],"presents":[38],"theoretical":[40],"analysis":[41],"of":[42,74],"this":[43],"method.":[44],"We":[45],"show":[46],"approach":[49],"used":[50],"generate":[52],"smoothed":[54],"is":[56,67],"equivalent":[57],"Kalman":[60,85],"filter.":[61],"result":[63],"demonstrates":[64],"there":[66],"strong":[69],"relationship":[70],"dynamics":[73],"delta":[75],"features":[76],"(and":[77],"delta-delta":[78],"features)":[79],"in":[80],"HMM-based":[81],"filter":[86],"dynamics.":[87]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}