{"id":"https://openalex.org/W788688893","doi":"https://doi.org/10.21437/interspeech.2012-573","title":"Synthetic references for template-based ASR using posterior features","display_name":"Synthetic references for template-based ASR using posterior features","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W788688893","doi":"https://doi.org/10.21437/interspeech.2012-573","mag":"788688893"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-573","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/192642/files/Soldo_INTERSPEECH_2012.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029950654","display_name":"Serena Soldo","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Serena Soldo","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai-Doss","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2146","last_page":"2149"},"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":0.9994999766349792,"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":0.9955999851226807,"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":0.8030036687850952},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.7460408806800842},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6580838561058044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6408112645149231},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5939055681228638},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5509546995162964},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.434952974319458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4343324303627014},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4114343822002411},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3808925449848175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030036687850952},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.7460408806800842},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6580838561058044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6408112645149231},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5939055681228638},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5509546995162964},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.434952974319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343324303627014},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4114343822002411},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3808925449848175},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-573","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:192642","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192642","pdf_url":"https://infoscience.epfl.ch/record/192642/files/Soldo_INTERSPEECH_2012.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:192642","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192642","pdf_url":"https://infoscience.epfl.ch/record/192642/files/Soldo_INTERSPEECH_2012.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W788688893.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W58567859","https://openalex.org/W1526516369","https://openalex.org/W1555573064","https://openalex.org/W1560013842","https://openalex.org/W1562131275","https://openalex.org/W1564152904","https://openalex.org/W1949738355","https://openalex.org/W2049686551","https://openalex.org/W2098372067","https://openalex.org/W2107076535","https://openalex.org/W2148555175","https://openalex.org/W2170094513"],"related_works":["https://openalex.org/W2121300814","https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W4231091074","https://openalex.org/W1886613375","https://openalex.org/W4236081792","https://openalex.org/W2025614924","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"Recently,":[0],"the":[1,41,49,59,81,110,131],"use":[2,60,69],"of":[3,44,51,61,70,83,90],"phoneme":[4],"class-conditional":[5],"probabilities":[6],"as":[7],"features":[8,18,53],"(posterior":[9],"features)":[10],"for":[11],"template-based":[12,74],"ASR":[13,75],"has":[14],"been":[15,20],"proposed.":[16],"These":[17],"have":[19,140],"found":[21],"to":[22,25,64,79,130],"generalize":[23],"well":[24],"unseen":[26],"data":[27,85],"and":[28,48,94,97],"yield":[29,127],"better":[30],"systems":[31,47],"than":[32],"standard":[33],"spectral-based":[34],"features.":[35],"In":[36],"this":[37],"paper,":[38],"motivated":[39],"by":[40,109],"high":[42,141],"quality":[43],"current":[45],"text-to-speech":[46],"robustness":[50],"posterior":[52],"toward":[54],"undesired":[55],"variability,":[56],"we":[57,103],"investigate":[58,104],"synthetic":[62,71,106,123,137],"speech":[63,72,124,133],"generate":[65],"reference":[66],"templates.":[67],"The":[68],"in":[73],"not":[76],"only":[77],"allows":[78],"address":[80],"issue":[82],"in-domain":[84],"collection":[86],"but":[87],"also":[88],"expansion":[89],"vocabulary.":[91],"Using":[92],"75-":[93],"600-word":[95],"task-independent":[96],"speaker-independent":[98],"setup":[99],"on":[100,115],"Phonebook":[101],"database,":[102],"different":[105],"voices":[107,138],"produced":[108],"Festival":[111],"HTS-based":[112],"synthesizer":[113],"trained":[114],"CMU":[116],"ARCTIC":[117],"databases.":[118],"Our":[119],"study":[120],"shows":[121],"that":[122,139],"templates":[125],"can":[126],"performance":[128],"comparable":[129],"natural":[132],"templates,":[134],"especially":[135],"with":[136],"intelligibility.":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
