{"id":"https://openalex.org/W308614314","doi":"https://doi.org/10.21437/eurospeech.2001-637","title":"Crosslingual speech recognition with multilingual acoustic models based on agglomerative and tree-based triphone clustering","display_name":"Crosslingual speech recognition with multilingual acoustic models based on agglomerative and tree-based triphone clustering","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W308614314","doi":"https://doi.org/10.21437/eurospeech.2001-637","mag":"308614314"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-637","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5022346020","display_name":"Andrej \u017dgank","orcid":"https://orcid.org/0000-0002-1411-5293"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andrej Zgank","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112340106","display_name":"Bojan Imperl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bojan Imperl","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048229848","display_name":"Finn Tore Johansen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Finn Tore Johansen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072645144","display_name":"Zdravko Ka\u010di\u010d","orcid":"https://orcid.org/0000-0002-8934-0604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zdravko Kacic","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110392882","display_name":"Bogomir Horvat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogomir Horvat","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022346020"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6362,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9014884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2725","last_page":"2729"},"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7759107351303101},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7751128077507019},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6579789519309998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5921346545219421},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5745850205421448},{"id":"https://openalex.org/keywords/norwegian","display_name":"Norwegian","score":0.5549823641777039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.531527578830719},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4992518424987793},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46857950091362},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.44504451751708984},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34251290559768677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10810145735740662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759107351303101},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7751128077507019},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6579789519309998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5921346545219421},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5745850205421448},{"id":"https://openalex.org/C63428231","wikidata":"https://www.wikidata.org/wiki/Q9043","display_name":"Norwegian","level":2,"score":0.5549823641777039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531527578830719},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4992518424987793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46857950091362},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.44504451751708984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34251290559768677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10810145735740662},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2001-637","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W47568227","https://openalex.org/W127087823","https://openalex.org/W144374866","https://openalex.org/W1502898378","https://openalex.org/W1644467064","https://openalex.org/W1841961279","https://openalex.org/W1886381962","https://openalex.org/W1956164794","https://openalex.org/W2132534451","https://openalex.org/W2141941513","https://openalex.org/W2158069733","https://openalex.org/W2587033535"],"related_works":["https://openalex.org/W2061564463","https://openalex.org/W2512753411","https://openalex.org/W2028240842","https://openalex.org/W1972562838","https://openalex.org/W2325410321","https://openalex.org/W4233839983","https://openalex.org/W3101822383","https://openalex.org/W1536194326","https://openalex.org/W3179137071","https://openalex.org/W2425515292"],"abstract_inverted_index":{"The":[0,34,60,70,83,106,124],"paper":[1],"describes":[2],"our":[3],"ongoing":[4],"work":[5],"on":[6,11,40,46,66,89],"crosslingual":[7,84,126],"speech":[8,85],"recognition":[9,86,120,130],"based":[10,39,65],"multilingual":[12],"triphone":[13,28,32],"hidden":[14],"Markov":[15],"models.":[16],"Multilingual":[17],"acoustic":[18],"models":[19],"were":[20,79,122],"built":[21],"using":[22],"two":[23],"different":[24,118],"clustering":[25,29,36,62],"procedures:":[26],"agglomerative":[27,35],"and":[30,73],"tree-based":[31,61],"clustering.":[33],"procedure":[37,63],"is":[38,54,64],"measuring":[41],"the":[42,51,57,90,101,114,135],"similarity":[43,53],"of":[44,108,132],"triphones":[45],"a":[47,129],"phoneme":[48],"level":[49],"where":[50],"monophone":[52],"estimated":[55],"by":[56],"Houtgast":[58],"algorithm.":[59],"common":[67],"broad":[68],"classes.":[69],"Slovenian,":[71],"German":[72],"Spanish":[74],"1000":[75,92],"FDB":[76,93],"SpeechDat(II)":[77,94],"databases":[78],"used":[80],"for":[81],"training.":[82],"was":[87,104,111],"performed":[88],"Norwegian":[91,102,109,119,137],"database.":[95],"No":[96],"adaptation":[97],"or":[98],"training":[99],"with":[100,113],"database":[103],"used.":[105],"mapping":[107],"phonemes":[110],"done":[112],"IPA":[115],"scheme.":[116],"Five":[117],"vocabularies":[121],"generated.":[123],"best":[125],"system":[127,138],"achieved":[128,139],"rate":[131],"45.03%,":[133],"while":[134],"reference":[136],"78.32%.":[140]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}