{"id":"https://openalex.org/W1996716433","doi":"https://doi.org/10.1109/slt.2012.6424229","title":"What makes this voice sound so bad? A multidimensional analysis of state-of-the-art text-to-speech systems","display_name":"What makes this voice sound so bad? A multidimensional analysis of state-of-the-art text-to-speech systems","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1996716433","doi":"https://doi.org/10.1109/slt.2012.6424229","mag":"1996716433"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","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/A5082812594","display_name":"Florian Hinterleitner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093367","display_name":"Deutsche Telekom (Germany)","ror":"https://ror.org/00m8prc86","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093367"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Florian Hinterleitner","raw_affiliation_strings":["Quality and Usability Lab, Telekom Innovation Laboratories, Technical University of Berlin, Germany","[Quality and Usability Lab, Telekom Innovation Laboratories, TU Berlin, Germany]"],"affiliations":[{"raw_affiliation_string":"Quality and Usability Lab, Telekom Innovation Laboratories, Technical University of Berlin, Germany","institution_ids":["https://openalex.org/I4210093367","https://openalex.org/I4577782"]},{"raw_affiliation_string":"[Quality and Usability Lab, Telekom Innovation Laboratories, TU Berlin, Germany]","institution_ids":["https://openalex.org/I4210093367","https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004988700","display_name":"Christoph Norrenbrock","orcid":"https://orcid.org/0000-0002-4792-0993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoph Norrenbrock","raw_affiliation_strings":["Digital Signal Processing and System Theory, CAU Kiel, Germany"],"affiliations":[{"raw_affiliation_string":"Digital Signal Processing and System Theory, CAU Kiel, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075001284","display_name":"Sebastian M\u00f6ller","orcid":"https://orcid.org/0000-0003-3057-0760"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]},{"id":"https://openalex.org/I4210093367","display_name":"Deutsche Telekom (Germany)","ror":"https://ror.org/00m8prc86","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093367"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Moller","raw_affiliation_strings":["Quality and Usability Lab, Telekom Innovation Laboratories, Technical University of Berlin, Germany","[Quality and Usability Lab, Telekom Innovation Laboratories, TU Berlin, Germany]"],"affiliations":[{"raw_affiliation_string":"Quality and Usability Lab, Telekom Innovation Laboratories, Technical University of Berlin, Germany","institution_ids":["https://openalex.org/I4210093367","https://openalex.org/I4577782"]},{"raw_affiliation_string":"[Quality and Usability Lab, Telekom Innovation Laboratories, TU Berlin, Germany]","institution_ids":["https://openalex.org/I4210093367","https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032405422","display_name":"Ulrich Heute","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ulrich Heute","raw_affiliation_strings":["Digital Signal Processing and System Theory, CAU Kiel, Germany"],"affiliations":[{"raw_affiliation_string":"Digital Signal Processing and System Theory, CAU Kiel, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082812594"],"corresponding_institution_ids":["https://openalex.org/I4210093367","https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":2.1407,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88014801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"240","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9100000262260437,"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":0.9100000262260437,"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/naturalness","display_name":"Naturalness","score":0.8629249334335327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.71620774269104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6674741506576538},{"id":"https://openalex.org/keywords/multidimensional-scaling","display_name":"Multidimensional scaling","score":0.6499223709106445},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6075590252876282},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5927462577819824},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5797408223152161},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4641851782798767},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43803197145462036},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1682780385017395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16198468208312988},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1540038287639618},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10220077633857727}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8629249334335327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.71620774269104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674741506576538},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.6499223709106445},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6075590252876282},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5927462577819824},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5797408223152161},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4641851782798767},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43803197145462036},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1682780385017395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16198468208312988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1540038287639618},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10220077633857727},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2012.6424229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1973192023","https://openalex.org/W2058409729","https://openalex.org/W2130750986","https://openalex.org/W2145496876","https://openalex.org/W2293077345","https://openalex.org/W2395003304","https://openalex.org/W2495084345","https://openalex.org/W3046579346","https://openalex.org/W4235611253","https://openalex.org/W6679444163","https://openalex.org/W6697027688","https://openalex.org/W6712055015"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"research":[3],"on":[4,55,96],"perceptual":[5,28,83],"quality":[6,84,115],"dimensions":[7,61,74,85,104],"of":[8,67,99],"synthetic":[9,118],"speech.":[10,119],"We":[11],"generated":[12],"57":[13],"stimuli":[14],"from":[15,86],"16/19":[16],"female/male":[17],"German":[18],"text-to-speech":[19],"systems":[20],"(TTS)":[21],"and":[22,49,71,79],"asked":[23],"listeners":[24],"to":[25,52,65,81,111],"judge":[26],"the":[27,59,82,91,97,109],"distances":[29],"between":[30],"them":[31],"in":[32,77,108],"a":[33,37,50,113],"sorting":[34],"task.":[35],"Through":[36],"subsequent":[38],"multidimensional":[39,88],"scaling":[40],"algorithm,":[41],"we":[42],"extracted":[43],"three":[44,60],"dimensions.":[45],"Via":[46],"expert":[47],"listening":[48],"comparison":[51],"ratings":[53],"gathered":[54],"16":[56],"attribute":[57],"scales,":[58],"can":[62],"be":[63,106],"assigned":[64],"naturalness":[66],"voice,":[68],"temporal":[69],"distortions":[70],"calmness.":[72],"These":[73],"are":[75,93],"discussed":[76],"detail":[78],"compared":[80],"previous":[87],"analyses.":[89],"Moreover,":[90],"results":[92],"analyzed":[94],"depending":[95],"type":[98],"TTS":[100],"system.":[101],"The":[102],"identified":[103],"will":[105],"used":[107],"future":[110],"build":[112],"dimension-based":[114],"predictor":[116],"for":[117]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
