{"id":"https://openalex.org/W2972949775","doi":"https://doi.org/10.21437/ssw.2019-22","title":"Measuring the contribution to cognitive load of each predicted vocoder speech parameter in DNN-based speech synthesis","display_name":"Measuring the contribution to cognitive load of each predicted vocoder speech parameter in DNN-based speech synthesis","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2972949775","doi":"https://doi.org/10.21437/ssw.2019-22","mag":"2972949775"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f0070db3-262f-420f-b539-9e2c16bb53cd","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015106629","display_name":"Avashna Govender","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":true,"raw_author_name":"Avashna Govender","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"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":"Cassia Valentini-Botinhao","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, 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":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015106629"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.5786,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76033268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"126"},"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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":0.733106255531311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6363531351089478},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5724002122879028},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5119960904121399},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4541636109352112},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4297581911087036},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4113616347312927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36269715428352356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733106255531311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6363531351089478},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5724002122879028},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5119960904121399},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4541636109352112},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4297581911087036},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4113616347312927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36269715428352356},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/ssw.2019-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f0070db3-262f-420f-b539-9e2c16bb53cd","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f0070db3-262f-420f-b539-9e2c16bb53cd","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Govender, A, Valentini-Botinhao, C & King, S 2019, Measuring the contribution to cognitive load of each predicted vocoder speech parameter in DNN-based speech synthesis. in Proceedings of the 10th ISCA Speech Synthesis Workshop. International Speech Communication Association, pp. 121-126, The 10th ISCA Speech Synthesis Workshop, Vienna, Austria, 20/09/19. https://doi.org/10.21437/SSW.2019-22","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f0070db3-262f-420f-b539-9e2c16bb53cd","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/SSW_2019/abstracts/SSW10_O_4-1.html","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":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f0070db3-262f-420f-b539-9e2c16bb53cd","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f0070db3-262f-420f-b539-9e2c16bb53cd","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Govender, A, Valentini-Botinhao, C & King, S 2019, Measuring the contribution to cognitive load of each predicted vocoder speech parameter in DNN-based speech synthesis. in Proceedings of the 10th ISCA Speech Synthesis Workshop. International Speech Communication Association, pp. 121-126, The 10th ISCA Speech Synthesis Workshop, Vienna, Austria, 20/09/19. https://doi.org/10.21437/SSW.2019-22","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1573337543","https://openalex.org/W1976339519","https://openalex.org/W2001718425","https://openalex.org/W2017057152","https://openalex.org/W2034049156","https://openalex.org/W2061099699","https://openalex.org/W2062242288","https://openalex.org/W2141936912","https://openalex.org/W2160780129","https://openalex.org/W2162488555","https://openalex.org/W2163010125","https://openalex.org/W2318778994","https://openalex.org/W2471520273","https://openalex.org/W2598638573","https://openalex.org/W2888844474","https://openalex.org/W2888911607","https://openalex.org/W4237834911"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4253660971","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469"],"abstract_inverted_index":{"Listening":[0],"to":[1,49,72,127],"even":[2],"high":[3],"quality":[4],"text-to-speech":[5,74],"-":[6,20],"such":[7],"as":[8],"that":[9,66,121],"generated":[10,75],"by":[11,43],"a":[12,18,62,77,107],"Deep":[13,78],"Neural":[14,79],"Network":[15,80],"(DNN)":[16],"driving":[17],"vocoder":[19,40],"still":[21],"requires":[22],"greater":[23],"cognitive":[24,129],"effort":[25],"than":[26],"natural":[27],"speech,":[28],"under":[29],"noisy":[30],"conditions.":[31],"Vocoding":[32],"itself,":[33],"plus":[34],"errors":[35],"in":[36,111],"predictions":[37],"of":[38,57,64],"the":[39,44,55,118],"speech":[41,86,95,124],"parameters":[42,87,96],"DNN":[45],"model":[46],"are":[47],"assumed":[48],"be":[50],"responsible.":[51],"To":[52],"better":[53],"understand":[54],"contribution":[56],"each":[58,122],"parameter,":[59],"we":[60],"construct":[61],"range":[63],"systems":[65],"vary":[67],"from":[68,91,100],"copysynthesis":[69],"(i.e.,":[70],"vocoding)":[71],"full":[73],"using":[76,106],"system.":[81],"Each":[82],"system":[83],"combines":[84],"some":[85],"(e.g.,":[88,97],"spectral":[89],"envelope)":[90],"copy-synthesis":[92],"with":[93],"other":[94],"F0)":[98],"predicted":[99,123],"text.":[101],"Cognitive":[102],"load":[103],"was":[104],"measured":[105],"pupillometry":[108],"paradigm":[109],"described":[110],"our":[112],"previous":[113],"work.":[114],"Our":[115],"results":[116],"reveal":[117],"differing":[119],"contributions":[120],"parameter":[125],"makes":[126],"increasing":[128],"load.<br/>":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
