{"id":"https://openalex.org/W2103126253","doi":"https://doi.org/10.1109/asru.2009.5373272","title":"A hierarchical structure for modeling inter and intra phonetic information for phoneme recognition","display_name":"A hierarchical structure for modeling inter and intra phonetic information for phoneme recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2103126253","doi":"https://doi.org/10.1109/asru.2009.5373272","mag":"2103126253"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5010513210","display_name":"Daniel V\u00e1squez","orcid":"https://orcid.org/0000-0003-4834-7268"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniel Vasquez","raw_affiliation_strings":["Institute of Information Technology, University of Ulm (EBS), Ulm, Germany","University of Ulm, Institute of Information Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, University of Ulm (EBS), Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]},{"raw_affiliation_string":"University of Ulm, Institute of Information Technology, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048934331","display_name":"Guillermo Aradilla","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Guillermo Aradilla","raw_affiliation_strings":["Nuance Communications, Speech Technologies Group, Ulm, Germany","Nuance Communications, Speech Technologies, Ulm, Germany"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Speech Technologies Group, Ulm, Germany","institution_ids":["https://openalex.org/I1292318990"]},{"raw_affiliation_string":"Nuance Communications, Speech Technologies, Ulm, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020458334","display_name":"Rainer Gruhn","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Gruhn","raw_affiliation_strings":["Institute of Information Technology, University of Ulm (EBS), Ulm, Germany","University of Ulm, Institute of Information Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, University of Ulm (EBS), Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]},{"raw_affiliation_string":"University of Ulm, Institute of Information Technology, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110317553","display_name":"Wolfgang Minker","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Minker","raw_affiliation_strings":["Institute of Information Technology, University of Ulm (EBS), Ulm, Germany","University of Ulm, Institute of Information Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, University of Ulm (EBS), Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]},{"raw_affiliation_string":"University of Ulm, Institute of Information Technology, Germany","institution_ids":["https://openalex.org/I196349391"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010513210"],"corresponding_institution_ids":["https://openalex.org/I196349391"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11208616,"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":"124","last_page":"129"},"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/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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9977999925613403,"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":0.8279501795768738},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.778716504573822},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6994484663009644},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6415897011756897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5726287364959717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5169493556022644},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.4930059611797333},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4418289363384247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4032120406627655},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.353135347366333},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3331736624240875},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12880688905715942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279501795768738},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.778716504573822},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6994484663009644},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6415897011756897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5726287364959717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169493556022644},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4930059611797333},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4418289363384247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4032120406627655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.353135347366333},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3331736624240875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12880688905715942},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322748","display_name":"Vysok\u00e9 U\u010den\u00ed Technick\u00e9 v Brn\u011b","ror":"https://ror.org/03613d656"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W186915233","https://openalex.org/W336107121","https://openalex.org/W811578723","https://openalex.org/W1491198847","https://openalex.org/W1494604982","https://openalex.org/W1553004968","https://openalex.org/W2077804127","https://openalex.org/W2102519965","https://openalex.org/W2103372210","https://openalex.org/W2125534887","https://openalex.org/W2159510016","https://openalex.org/W2167763959","https://openalex.org/W6611441213","https://openalex.org/W6675577069"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2148099973","https://openalex.org/W2340308015","https://openalex.org/W4213426189"],"abstract_inverted_index":{"In":[0,79],"this":[1,80,121],"paper,":[2,81],"we":[3,82],"present":[4],"a":[5,26],"two-layer":[6],"hierarchical":[7,36,99],"structure":[8,18],"based":[9],"on":[10,52,75,108,120],"neural":[11],"networks":[12],"for":[13],"phoneme":[14,102],"recognition.":[15],"The":[16],"proposed":[17,62],"attempts":[19],"to":[20,70,95,115],"model":[21,63],"only":[22],"the":[23,39,44,48,54,61,76,86,109,116],"characteristics":[24],"within":[25],"phoneme,":[27],"i.e.,":[28],"intra-phonetic":[29,45],"information.":[30,57,78],"This":[31],"differs":[32],"from":[33],"other":[34,97],"state-of-the-art":[35,98],"structures":[37],"where":[38],"first":[40],"layer":[41,50,72],"typically":[42],"models":[43],"information":[46,92],"while":[47],"second":[49],"focuses":[51,74],"modeling":[53],"contextual":[55],"(inter-phonetic)":[56],"An":[58],"advantage":[59],"of":[60,104],"is":[64,106],"that":[65,73,85],"it":[66],"can":[67],"be":[68],"added":[69],"another":[71],"inter-phonetic":[77,91],"also":[83,93],"show":[84],"categorization":[87],"between":[88],"intra-":[89],"and":[90],"allows":[94],"extend":[96],"approaches.":[100],"A":[101],"accuracy":[103],"77.89%":[105],"achieved":[107],"TIMIT":[110],"database,":[111],"which":[112],"compares":[113],"favorably":[114],"best":[117],"results":[118],"obtained":[119],"database.":[122]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}