{"id":"https://openalex.org/W226412370","doi":"https://doi.org/10.21437/interspeech.2007-226","title":"A system for transforming the emotion in speech: combining data-driven conversion techniques for prosody and voice quality","display_name":"A system for transforming the emotion in speech: combining data-driven conversion techniques for prosody and voice quality","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W226412370","doi":"https://doi.org/10.21437/interspeech.2007-226","mag":"226412370"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5068805021","display_name":"Zeynep Inanoglu","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":"Zeynep Inanoglu","raw_affiliation_strings":["University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109097977","display_name":"Steve Young","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":"Steve Young","raw_affiliation_strings":["University of Cambridge,"],"raw_orcid":null,"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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3596,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94002959,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"490","last_page":"493"},"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":0.9993000030517578,"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":0.9976999759674072,"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/speech-recognition","display_name":"Speech recognition","score":0.7932517528533936},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7058309316635132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695145845413208},{"id":"https://openalex.org/keywords/sadness","display_name":"Sadness","score":0.6867759823799133},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6681225895881653},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5242089033126831},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5215358734130859},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4735153019428253},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.4425511062145233},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.4168434739112854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4140082597732544},{"id":"https://openalex.org/keywords/anger","display_name":"Anger","score":0.36387205123901367},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21317413449287415},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11029383540153503}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7932517528533936},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7058309316635132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695145845413208},{"id":"https://openalex.org/C2779812673","wikidata":"https://www.wikidata.org/wiki/Q169251","display_name":"Sadness","level":3,"score":0.6867759823799133},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6681225895881653},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5242089033126831},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5215358734130859},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4735153019428253},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.4425511062145233},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.4168434739112854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4140082597732544},{"id":"https://openalex.org/C2779302386","wikidata":"https://www.wikidata.org/wiki/Q79871","display_name":"Anger","level":2,"score":0.36387205123901367},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21317413449287415},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11029383540153503},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2007-226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.119.9392","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.119.9392","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/~sjy/papers/inyo07.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:325220","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/325220/","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"},{"id":"pmh:oai:generic.eprints.org:343324","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/343324/","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":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W39968598","https://openalex.org/W204428907","https://openalex.org/W1588037970","https://openalex.org/W1589602221","https://openalex.org/W2091850880","https://openalex.org/W2150791533","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2161135987","https://openalex.org/W2161736993"],"related_works":["https://openalex.org/W71705338","https://openalex.org/W4214652783","https://openalex.org/W258725851","https://openalex.org/W2810172795","https://openalex.org/W4388134110","https://openalex.org/W2400641934","https://openalex.org/W2018346846","https://openalex.org/W2028755160","https://openalex.org/W2041541161","https://openalex.org/W3167551411"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,12,31,76,82,142],"system":[4,21,117],"that":[5,26,110,140],"combines":[6],"independent":[7,96],"transformation":[8],"techniques":[9],"to":[10],"endow":[11],"neutral":[13],"utterance":[14],"with":[15,120],"some":[16],"required":[17],"target":[18],"emotion.":[19],"The":[20,105],"consists":[22],"of":[23,34,112,123,130,141],"three":[24,92],"modules":[25],"are":[27,45,55],"each":[28],"trained":[29],"on":[30,39],"limited":[32],"amount":[33],"speech":[35,126,148],"data":[36,88],"and":[37,47,81,132],"act":[38],"differing":[40],"temporal":[41],"layers.":[42],"F0":[43],"contours":[44],"modelled":[46],"generated":[48],"using":[49,57,94],"context-sensitive":[50],"syllable":[51],"HMMs,":[52],"while":[53,127],"durations":[54],"transformed":[56],"phone-based":[58],"relative":[59],"decision":[60],"trees.":[61],"For":[62],"spectral":[63],"conversion":[64,79,153],"which":[65],"is":[66],"applied":[67],"at":[68],"the":[69,121,128],"segmental":[70],"level,":[71],"two":[72],"methods":[73],"were":[74,89],"investigated:":[75],"GMM-based":[77],"voice":[78,152],"approach":[80],"codebook":[83],"selection":[84],"approach.":[85],"Converted":[86],"test":[87,107],"evaluated":[90],"for":[91],"emotions":[93],"an":[95],"emotion":[97,150],"classifier":[98],"as":[99,101],"well":[100],"perceptual":[102],"listening":[103,106],"tests.":[104],"results":[108],"show":[109],"perception":[111,122,129],"sadness":[113],"output":[114],"by":[115],"our":[116],"was":[118,134],"comparable":[119],"human":[124,143],"sad":[125],"surprise":[131],"anger":[133],"around":[135],"5":[136],"%":[137],"worse":[138],"than":[139],"speaker.":[144],"Index":[145],"Terms:":[146],"expressive":[147],"synthesis,":[149],"conversion,":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}