{"id":"https://openalex.org/W1553129813","doi":"https://doi.org/10.21437/interspeech.2009-430","title":"Speech recognition with speech synthesis models by marginalising over decision tree leaves","display_name":"Speech recognition with speech synthesis models by marginalising over decision tree leaves","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1553129813","doi":"https://doi.org/10.21437/interspeech.2009-430","mag":"1553129813"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/145970/files/Dines_INTERSPEECH-2_2009.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","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":true,"raw_author_name":"John Dines","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017257483","display_name":"Lakshmi Babu Saheer","orcid":"https://orcid.org/0000-0002-5263-596X"},"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":"Lakshmi Saheer","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068810492","display_name":"Hui Liang","orcid":"https://orcid.org/0000-0001-6632-0929"},"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":"Hui Liang","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105301736"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":4.0647,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93639245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1395","last_page":"1398"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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":0.8345581293106079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.684012770652771},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5942293405532837},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5914550423622131},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5892709493637085},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5596738457679749},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.499096155166626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49292445182800293},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4553535282611847},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07756796479225159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345581293106079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.684012770652771},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5942293405532837},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5914550423622131},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5892709493637085},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5596738457679749},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.499096155166626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49292445182800293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4553535282611847},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07756796479225159},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2009-430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:145970","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145970","pdf_url":"https://infoscience.epfl.ch/record/145970/files/Dines_INTERSPEECH-2_2009.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":"http://infoscience.epfl.ch/record/145970","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:146385","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146385","pdf_url":"https://infoscience.epfl.ch/record/146385/files/Dines_Idiap-RR-17-2009.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":"http://infoscience.epfl.ch/record/146385","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.333.56","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.333.56","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2009/Dines_Idiap-RR-17-2009.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:145970","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145970","pdf_url":"https://infoscience.epfl.ch/record/145970/files/Dines_INTERSPEECH-2_2009.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":"http://infoscience.epfl.ch/record/145970","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1553129813.pdf","grobid_xml":"https://content.openalex.org/works/W1553129813.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1518816749","https://openalex.org/W1529897604","https://openalex.org/W1580849279","https://openalex.org/W1593598571","https://openalex.org/W1599512239","https://openalex.org/W2054264739","https://openalex.org/W2090861223","https://openalex.org/W2119929864","https://openalex.org/W2165856656","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W2385319785"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"increasing":[3],"interest":[4],"in":[5,19,101],"the":[6,12,20,36,62,96,127],"use":[7,82,97],"of":[8,14,22,38,64,86,98,121,140,157],"unsupervised":[9,65],"adaptation":[10,33,66],"for":[11,61],"personalisation":[13],"text-to-speech":[15],"(TTS)":[16],"voices,":[17],"particularly":[18],"context":[21],"speech-to-speech":[23],"translation.":[24],"This":[25],"requires":[26],"that":[27,47,113,130],"we":[28,108],"are":[29,131],"able":[30],"to":[31,56,67,91],"generate":[32],"transforms":[34,70],"from":[35,117],"output":[37],"an":[39,58],"automatic":[40],"speech":[41,148,162,164],"recognition":[42,149],"(ASR)":[43],"system.":[44],"An":[45],"approach":[46,112],"utilises":[48],"unified":[49,79,168],"ASR":[50,75,102,115],"and":[51,76,103,151],"TTS":[52,68,122,128],"models":[53,80,116,123,169],"would":[54],"seem":[55],"offer":[57],"ideal":[59],"mechanism":[60],"application":[63],"since":[69],"could":[71],"be":[72],"shared":[73],"between":[74],"TTS.":[77,104],"Such":[78],"should":[81],"a":[83,110,118,145],"common":[84],"set":[85,120],"parameters.":[87],"A":[88],"major":[89],"barrier":[90],"such":[92],"parameter":[93],"sharing":[94],"is":[95],"differing":[99],"contexts":[100,129],"In":[105],"this":[106,158],"paper":[107],"propose":[109],"simple":[111],"generates":[114],"trained":[119],"by":[124,134],"marginalising":[125],"over":[126],"not":[132],"used":[133],"ASR.":[135],"We":[136],"present":[137],"preliminary":[138],"results":[139],"our":[141],"proposed":[142],"method":[143],"on":[144],"large":[146],"vocabulary":[147],"task":[150],"provide":[152],"insights":[153],"into":[154],"future":[155],"directions":[156],"work.":[159],"Index":[160],"Terms:":[161],"synthesis,":[163],"recognition,":[165],"decision":[166],"trees,":[167]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
