{"id":"https://openalex.org/W1120805016","doi":"https://doi.org/10.21437/interspeech.2015-126","title":"Deep neural network context embeddings for model selection in rich-context HMM synthesis","display_name":"Deep neural network context embeddings for model selection in rich-context HMM synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1120805016","doi":"https://doi.org/10.21437/interspeech.2015-126","mag":"1120805016"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/19840195/Merritt_Interspeech2015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2207","last_page":"2211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9976999759674072,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7376382946968079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726263701915741},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.683654248714447},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6396507620811462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6058279275894165},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5912948846817017},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5280821323394775},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5190311670303345},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.49736979603767395},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4799244999885559},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4697354733943939},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4523221254348755},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.413821816444397},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1184782087802887},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05562606453895569}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7376382946968079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726263701915741},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.683654248714447},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6396507620811462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6058279275894165},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5912948846817017},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5280821323394775},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5190311670303345},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.49736979603767395},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4799244999885559},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4697354733943939},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4523221254348755},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.413821816444397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1184782087802887},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05562606453895569},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2015-126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7dc92d2d-21aa-4d3c-b914-5ad5e75c6a48","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7dc92d2d-21aa-4d3c-b914-5ad5e75c6a48","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19840195/Merritt_Interspeech2015.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"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-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.716.2421","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.716.2421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2015/merritt2015RichContext.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.912.2542","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.912.2542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.zhizheng.org/papers/is2015_tom_rich.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/7dc92d2d-21aa-4d3c-b914-5ad5e75c6a48","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7dc92d2d-21aa-4d3c-b914-5ad5e75c6a48","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19840195/Merritt_Interspeech2015.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"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-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1120805016.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W156280357","https://openalex.org/W197380572","https://openalex.org/W1499332833","https://openalex.org/W1544516254","https://openalex.org/W1568585903","https://openalex.org/W1992287499","https://openalex.org/W2000513720","https://openalex.org/W2033178790","https://openalex.org/W2078597717","https://openalex.org/W2098372067","https://openalex.org/W2108048146","https://openalex.org/W2109444541","https://openalex.org/W2123140629","https://openalex.org/W2129142580","https://openalex.org/W2152205330","https://openalex.org/W2154920538","https://openalex.org/W2188827208","https://openalex.org/W2277581165","https://openalex.org/W2296681920","https://openalex.org/W2395264448","https://openalex.org/W2401318443","https://openalex.org/W2915863225","https://openalex.org/W2915960560","https://openalex.org/W2916535084","https://openalex.org/W2917245127"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,19,30,103,116,141],"novel":[4],"form":[5],"of":[6,18,27,88,97,106,126],"parametric":[7,99],"synthesis":[8,35,129],"that":[9,80,115],"uses":[10],"context":[11,109,137],"embeddings":[12,138],"produced":[13],"by":[14],"the":[15,25,48,89,94,107],"bottleneck":[16],"layer":[17],"deep":[20,151],"neural":[21,142,152],"network":[22],"to":[23,66,70,93,123],"guide":[24,124],"selection":[26,125],"models":[28,61],"in":[29,37,47],"rich-context":[31],"HMM-based":[32],"synthesiser.":[33],"Rich-context":[34],"\u2013":[36,62],"which":[38],"Gaussian":[39],"distributions":[40],"estimated":[41],"from":[42,140],"single":[43],"lin-guistic":[44],"contexts":[45,84],"seen":[46],"training":[49],"data":[50],"are":[51],"used":[52,122],"for":[53],"synthesis,":[54,147],"rather":[55],"than":[56],"more":[57],"conventional":[58,117],"decision":[59],"tree-tied":[60],"was":[63],"originally":[64],"proposed":[65,132],"address":[67],"over-smoothing":[68],"due":[69],"averag-ing":[71],"across":[72,82],"contexts.":[73],"Our":[74,131],"previous":[75],"investigations":[76],"have":[77],"confirmed":[78],"experimentally":[79],"averaging":[81],"different":[83],"is":[85,114,120],"in-deed":[86],"one":[87],"largest":[90],"factors":[91],"contributing":[92],"limited":[95],"quality":[96],"statistical":[98],"speech":[100,146],"synthesis.":[101],"However,":[102],"possible":[104],"weakness":[105],"rich":[108,154],"approach":[110,133],"as":[111],"previously":[112],"formulated":[113],"tied":[118],"model":[119],"still":[121],"Gaussians":[127],"at":[128],"time.":[130],"replaces":[134],"this":[135],"with":[136],"derived":[139],"network.":[143],"Index":[144],"Terms:":[145],"hidden":[148],"Markov":[149],"model,":[150],"networks,":[153],"context,":[155],"embedding":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}