{"id":"https://openalex.org/W1963854073","doi":"https://doi.org/10.1109/icassp.2010.5495562","title":"Simple methods for improving speaker-similarity of HMM-based speech synthesis","display_name":"Simple methods for improving speaker-similarity of HMM-based speech synthesis","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1963854073","doi":"https://doi.org/10.1109/icassp.2010.5495562","mag":"1963854073"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"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":"Junichi Yamagishi","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4610","last_page":"4613"},"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":0.9968000054359436,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7124729156494141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464364528656006},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5703184604644775},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5486173033714294},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4390038549900055},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4329957365989685},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4149261713027954},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.41234180331230164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4048394560813904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37762829661369324},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.12245053052902222}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7124729156494141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464364528656006},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5703184604644775},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5486173033714294},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4390038549900055},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4329957365989685},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4149261713027954},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.41234180331230164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4048394560813904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37762829661369324},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.12245053052902222},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2010.5495562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.2475","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.2475","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/2010/JunichiICASSP10.pdf","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/4544","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/4544","pdf_url":null,"source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/58203055-ed8d-49d3-ab1a-333ad22d72a7","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/58203055-ed8d-49d3-ab1a-333ad22d72a7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W129305155","https://openalex.org/W1529897604","https://openalex.org/W1564152904","https://openalex.org/W1580849279","https://openalex.org/W1995453281","https://openalex.org/W2028138004","https://openalex.org/W2034277951","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2093632031","https://openalex.org/W2111194146","https://openalex.org/W2119929864","https://openalex.org/W2129142580","https://openalex.org/W2135934764","https://openalex.org/W2170980774","https://openalex.org/W3142087749","https://openalex.org/W6631636991","https://openalex.org/W6649534688","https://openalex.org/W6676358011","https://openalex.org/W6753612206","https://openalex.org/W6865107258"],"related_works":["https://openalex.org/W2341338763","https://openalex.org/W2419138286","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W101156158","https://openalex.org/W2182848507","https://openalex.org/W2387825067","https://openalex.org/W2506414444","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"In":[0,98],"this":[1],"paper":[2],"we":[3,58],"revisit":[4],"some":[5],"basic":[6],"configuration":[7],"choices":[8],"of":[9,26,35,44,50,70,104,114],"HMM-based":[10,46],"speech":[11,47,80,96],"synthesis,":[12],"such":[13],"as":[14,57],"waveform":[15,83],"sampling":[16,84],"rate,":[17],"auditory":[18],"frequency":[19],"warping":[20],"scale":[21],"and":[22,91,120,124],"the":[23,33,51,68,71],"logarithmic":[24,102],"scaling":[25],"F":[27,105,115],"<sub":[28,106,116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[29,107,117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[30,108,118],",":[31],"with":[32],"aim":[34],"improving":[36],"speaker":[37,93],"similarity":[38,94],"which":[39],"is":[40],"an":[41],"acknowledged":[42],"weakness":[43],"current":[45],"synthesisers.":[48],"All":[49],"techniques":[52],"investigated":[53],"are":[54],"simple":[55],"but,":[56],"demonstrate":[59],"using":[60],"perceptual":[61],"tests,":[62],"can":[63,86],"make":[64],"substantial":[65],"differences":[66],"to":[67,75],"quality":[69],"synthetic":[72],"speech.":[73],"Contrary":[74],"common":[76],"practice":[77],"in":[78,110],"automatic":[79],"recognition,":[81],"higher":[82],"rates":[85],"offer":[87],"enhanced":[88],"feature":[89],"extraction":[90],"improved":[92],"for":[95],"synthesis.":[97],"addition,":[99],"a":[100],"generalized":[101],"transform":[103],"results":[109],"larger":[111],"intra-utterance":[112],"variance":[113],"trajectories":[119],"hence":[121],"more":[122],"dynamic":[123],"natural-sounding":[125],"prosody.":[126]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}