{"id":"https://openalex.org/W2188827208","doi":"https://doi.org/10.21437/interspeech.2014-361","title":"Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech","display_name":"Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2188827208","doi":"https://doi.org/10.21437/interspeech.2014-361","mag":"2188827208"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"article","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/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, U.K","institution_ids":[]}]},{"author_position":"middle","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":false,"raw_author_name":"Matt Shannon","raw_affiliation_strings":["Department of Engineering, University of Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055797199","display_name":"Catherine Mayo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Catherine Mayo","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038417409"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6114,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97336051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9980000257492065,"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/T11309","display_name":"Music and Audio Processing","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7387338876724243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302893400192261},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6673562526702881},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6618159413337708},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5851610898971558},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4699452221393585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4478408992290497},{"id":"https://openalex.org/keywords/neurocomputational-speech-processing","display_name":"Neurocomputational speech processing","score":0.41709017753601074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3956416845321655},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17497554421424866}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7387338876724243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302893400192261},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6673562526702881},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6618159413337708},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5851610898971558},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4699452221393585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4478408992290497},{"id":"https://openalex.org/C202101335","wikidata":"https://www.wikidata.org/wiki/Q7002166","display_name":"Neurocomputational speech processing","level":4,"score":0.41709017753601074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3956416845321655},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17497554421424866},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2014-361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.707.4581","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.707.4581","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/%7Esms46/papers/henter2014measuring.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/d4654e05-2a0d-4e76-a6c9-38ad6e03697f","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d4654e05-2a0d-4e76-a6c9-38ad6e03697f","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W108207029","https://openalex.org/W573069471","https://openalex.org/W595249637","https://openalex.org/W1558306184","https://openalex.org/W1601809792","https://openalex.org/W1977049475","https://openalex.org/W1978741356","https://openalex.org/W1979449467","https://openalex.org/W1995332880","https://openalex.org/W2000513720","https://openalex.org/W2024083195","https://openalex.org/W2067752346","https://openalex.org/W2098372067","https://openalex.org/W2106554350","https://openalex.org/W2108048146","https://openalex.org/W2119929864","https://openalex.org/W2129142580","https://openalex.org/W2143029619","https://openalex.org/W2152205330","https://openalex.org/W2154920538","https://openalex.org/W2396043161","https://openalex.org/W2400063444","https://openalex.org/W2916535084","https://openalex.org/W3046579346","https://openalex.org/W3099839986","https://openalex.org/W4231807801"],"related_works":["https://openalex.org/W2909642128","https://openalex.org/W3202371450","https://openalex.org/W2092804354","https://openalex.org/W2770963694","https://openalex.org/W2098957603","https://openalex.org/W2016090750","https://openalex.org/W2153664791","https://openalex.org/W4225753921","https://openalex.org/W2188827208","https://openalex.org/W2470236000"],"abstract_inverted_index":{"Acoustic":[0],"models":[1],"used":[2,66],"for":[3],"statistical":[4],"parametric":[5],"speech":[6,36,48,110,120],"synthe-sis":[7],"typically":[8],"incorporate":[9],"many":[10],"modelling":[11,67],"assumptions.":[12],"It":[13],"is":[14],"an":[15],"open":[16],"question":[17],"to":[18,58,80],"what":[19],"extent":[20],"these":[21],"assumptions":[22],"limit":[23],"the":[24,60,75,91,102],"natu-ralness":[25],"of":[26,63,104],"synthesised":[27],"speech.":[28],"To":[29],"investigate":[30],"this":[31],"question,":[32],"we":[33,55],"recorded":[34],"a":[35],"corpus":[37],"where":[38],"each":[39],"prompt":[40],"was":[41],"read":[42],"aloud":[43],"multiple":[44],"times.":[45],"By":[46],"combining":[47],"parameter":[49,106],"trajectories":[50],"ex-tracted":[51],"from":[52],"different":[53],"repetitions,":[54],"were":[56],"able":[57],"quantify":[59],"perceptual":[61],"effects":[62],"certain":[64],"commonly":[65],"assump-tions.":[68],"Subjective":[69],"listening":[70],"tests":[71],"show":[72],"that":[73,93],"taking":[74],"source":[76],"and":[77],"filter":[78],"parameters":[79],"be":[81,95],"conditionally":[82],"independent,":[83],"or":[84],"using":[85],"di-agonal":[86],"covariance":[87,117],"matrices,":[88,118],"significantly":[89],"limits":[90],"naturalness":[92],"can":[94],"achieved.":[96],"Our":[97],"experimental":[98],"results":[99],"also":[100],"demonstrate":[101],"shortcomings":[103],"mean-based":[105],"generation.":[107],"Index":[108],"terms:":[109],"synthesis,":[111],"acoustic":[112],"modelling,":[113],"stream":[114],"in-dependence,":[115],"diagonal":[116],"repeated":[119],"1.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}