{"id":"https://openalex.org/W2098152933","doi":"https://doi.org/10.21437/interspeech.2010-184","title":"Autoregressive clustering for HMM speech synthesis","display_name":"Autoregressive clustering for HMM speech synthesis","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2098152933","doi":"https://doi.org/10.21437/interspeech.2010-184","mag":"2098152933"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-184","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.dspace.cam.ac.uk/handle/1810/226374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080404214","display_name":"Matt Shannon","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Matt Shannon","raw_affiliation_strings":["University of Cambridge,"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070594684","display_name":"Bill Byrne","orcid":"https://orcid.org/0000-0003-1896-4492"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"William Byrne","raw_affiliation_strings":["University of Cambridge,"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080404214"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.931,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81536687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"832"},"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":0.995199978351593,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9936000108718872,"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/autoregressive-model","display_name":"Autoregressive model","score":0.908859133720398},{"id":"https://openalex.org/keywords/nonlinear-autoregressive-exogenous-model","display_name":"Nonlinear autoregressive exogenous model","score":0.8573936223983765},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.7848799228668213},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6717810034751892},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6590353846549988},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6511971950531006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6021717190742493},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5989063382148743},{"id":"https://openalex.org/keywords/setar","display_name":"SETAR","score":0.5086265802383423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47791653871536255},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.4350183606147766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4138956069946289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4070049226284027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30180299282073975},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24553841352462769},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23977378010749817},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14645808935165405},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.14294952154159546},{"id":"https://openalex.org/keywords/autoregressive-integrated-moving-average","display_name":"Autoregressive integrated moving average","score":0.126636803150177}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.908859133720398},{"id":"https://openalex.org/C42536954","wikidata":"https://www.wikidata.org/wiki/Q7049462","display_name":"Nonlinear autoregressive exogenous model","level":3,"score":0.8573936223983765},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.7848799228668213},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6717810034751892},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6590353846549988},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6511971950531006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021717190742493},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5989063382148743},{"id":"https://openalex.org/C30795276","wikidata":"https://www.wikidata.org/wiki/Q7389877","display_name":"SETAR","level":5,"score":0.5086265802383423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47791653871536255},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.4350183606147766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4138956069946289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4070049226284027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30180299282073975},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24553841352462769},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23977378010749817},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14645808935165405},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.14294952154159546},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.126636803150177},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2010-184","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/226374","is_oa":true,"landing_page_url":"http://www.dspace.cam.ac.uk/handle/1810/226374","pdf_url":"http://www.dspace.cam.ac.uk/handle/1810/226374","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.295.9067","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.295.9067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mi.eng.cam.ac.uk/~sms46/papers/shannon2010autoregressive.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:323729","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/323729/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/226374","is_oa":true,"landing_page_url":"http://www.dspace.cam.ac.uk/handle/1810/226374","pdf_url":"http://www.dspace.cam.ac.uk/handle/1810/226374","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2098152933.pdf","grobid_xml":"https://content.openalex.org/works/W2098152933.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W70888257","https://openalex.org/W1511967608","https://openalex.org/W1514737389","https://openalex.org/W1833981795","https://openalex.org/W1926768285","https://openalex.org/W1935012542","https://openalex.org/W1963627370","https://openalex.org/W2000513720","https://openalex.org/W2051347452","https://openalex.org/W2061903919","https://openalex.org/W2116046013","https://openalex.org/W2119929864","https://openalex.org/W2129142580","https://openalex.org/W2140337865","https://openalex.org/W2158069733","https://openalex.org/W2162351465","https://openalex.org/W2406017614","https://openalex.org/W2599301895","https://openalex.org/W3017269856","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W4320078083","https://openalex.org/W2019155478","https://openalex.org/W1988789713","https://openalex.org/W1611117054","https://openalex.org/W4238343629","https://openalex.org/W1547559323","https://openalex.org/W3123153965","https://openalex.org/W304218021","https://openalex.org/W3004904934","https://openalex.org/W4287185323"],"abstract_inverted_index":{"The":[0],"autoregressive":[1,35,38,49,65,92,126],"HMM":[2,50,127],"has":[3],"been":[4],"shown":[5],"to":[6,54],"provide":[7],"efficient":[8],"parameter":[9],"estimation":[10],"and":[11,51],"high-quality":[12],"synthesis,":[13,122],"but":[14],"in":[15,116],"previous":[16],"experiments":[17],"decision":[18,44,123],"trees":[19],"derived":[20],"from":[21],"a":[22,105,113],"non-autoregressive":[23],"system":[24],"were":[25],"used.":[26],"In":[27],"this":[28],"paper":[29],"we":[30,102],"investigate":[31],"the":[32,48,55,68,71,77,91,95],"use":[33],"of":[34,70,97,108],"clustering":[36,46,57,66],"for":[37,47,84,90],"HMM-based":[39,120],"speech":[40,121],"synthesis.":[41],"We":[42,74],"describe":[43],"tree":[45,124],"highlight":[52],"differences":[53],"standard":[56,78],"procedure.":[58],"Subjective":[59],"listening":[60],"evaluation":[61],"results":[62],"suggest":[63],"that":[64,76,104],"improves":[67],"naturalness":[69],"resulting":[72],"speech.":[73],"find":[75,103],"minimum":[79],"description":[80],"length":[81],"(MDL)":[82],"criterion":[83],"selecting":[85],"model":[86,98],"complexity":[87,99],"is":[88,110],"inappropriate":[89],"HMM.":[93],"Investigating":[94],"effect":[96],"on":[100],"naturalness,":[101],"large":[106],"degree":[107],"overfitting":[109],"tolerated":[111],"without":[112],"substantial":[114],"decrease":[115],"naturalness.":[117],"Index":[118],"terms:":[119],"clustering,":[125],"1.":[128]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}