{"id":"https://openalex.org/W2116823866","doi":"https://doi.org/10.1109/icassp.2004.1326652","title":"Multilingual acoustic models for speech recognition and synthesis","display_name":"Multilingual acoustic models for speech recognition and synthesis","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2116823866","doi":"https://doi.org/10.1109/icassp.2004.1326652","mag":"2116823866"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5074068808","display_name":"Siegfried Kunzmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Kunzmann","raw_affiliation_strings":["European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","institution_ids":[]},{"raw_affiliation_string":"Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015413878","display_name":"Volker Fischer","orcid":"https://orcid.org/0000-0001-5437-4030"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Fischer","raw_affiliation_strings":["European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","institution_ids":[]},{"raw_affiliation_string":"Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103077297","display_name":"Johan Isay Guerrero Gonz\u00e1lez","orcid":"https://orcid.org/0009-0005-6758-2230"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Gonzalez","raw_affiliation_strings":["European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","institution_ids":[]},{"raw_affiliation_string":"Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074459569","display_name":"Ossama Emam","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"O. Emam","raw_affiliation_strings":["European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","institution_ids":[]},{"raw_affiliation_string":"Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085747961","display_name":"Carsten G\u00fcnther","orcid":"https://orcid.org/0000-0001-6585-5825"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Gunther","raw_affiliation_strings":["European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","institution_ids":[]},{"raw_affiliation_string":"Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064900060","display_name":"Eric Janke","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Janke","raw_affiliation_strings":["European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Voice Technology Development, IBM Pervasive Computing, Mannheim, Germany","institution_ids":[]},{"raw_affiliation_string":"Eur. Voice Technol. Dev., IBM Pervasive Comput., Mannheim, Germany","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":3.2378,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92396227,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"iii","last_page":"745"},"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":0.9965000152587891,"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":0.9955000281333923,"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":0.8101398944854736},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7500882148742676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.723038911819458},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.5839948058128357},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5828133821487427},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5634490251541138},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48297157883644104},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.473127543926239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34540948271751404},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33132317662239075},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13158240914344788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101398944854736},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7500882148742676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.723038911819458},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.5839948058128357},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5828133821487427},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5634490251541138},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48297157883644104},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.473127543926239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34540948271751404},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33132317662239075},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13158240914344788},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W88751538","https://openalex.org/W170354295","https://openalex.org/W280873630","https://openalex.org/W1569552814","https://openalex.org/W1577446345","https://openalex.org/W2033436836","https://openalex.org/W2116648050","https://openalex.org/W2138849432","https://openalex.org/W2405437190","https://openalex.org/W2543977149","https://openalex.org/W6610270533","https://openalex.org/W6713712427"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W2092406870","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"review":[4],"the":[5,42,50,60,68],"design":[6],"of":[7,25,44,52,62,70],"a":[8,26,63],"common":[9,64],"phone":[10,65],"alphabet":[11,66],"for":[12,49,67],"up":[13],"to":[14],"fifteen":[15],"languages":[16],"and":[17,34,55,58,75],"describe":[18,59],"its":[19],"application":[20],"in":[21],"two":[22],"important":[23],"components":[24],"seamless":[27],"multilingual":[28,45],"conversational":[29],"system,":[30],"namely":[31],"speech":[32,77],"recognition":[33,51],"synthesis.":[35],"We":[36],"report":[37],"on":[38],"experiments":[39],"that":[40],"demonstrate":[41],"advantages":[43],"acoustic":[46],"models":[47],"both":[48],"foreign":[53],"names":[54],"non-native":[56],"speech,":[57],"usefulness":[61],"construction":[69],"unit":[71],"selection":[72],"based":[73],"mono-":[74],"bilingual":[76],"synthesis":[78],"systems.":[79]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
