{"id":"https://openalex.org/W2401168617","doi":"https://doi.org/10.21437/interspeech.2013-105","title":"Predicting the quality of text-to-speech systems from a large-scale feature set","display_name":"Predicting the quality of text-to-speech systems from a large-scale feature set","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2401168617","doi":"https://doi.org/10.21437/interspeech.2013-105","mag":"2401168617"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-105","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/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":["Technical University of Berlin"],"affiliations":[{"raw_affiliation_string":"Technical University of Berlin","institution_ids":["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":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph R. Norrenbrock","raw_affiliation_strings":["University of Kiel,"],"affiliations":[{"raw_affiliation_string":"University of Kiel,","institution_ids":["https://openalex.org/I32021983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075001284","display_name":"Sebastian M\u00f6ller","orcid":"https://orcid.org/0000-0003-3057-0760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian M\u00f6ller","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032405422","display_name":"Ulrich Heute","orcid":null},"institutions":[{"id":"https://openalex.org/I32021983","display_name":"Kiel University","ror":"https://ror.org/04v76ef78","country_code":"DE","type":"education","lineage":["https://openalex.org/I32021983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulrich Heute","raw_affiliation_strings":["University of Kiel,"],"affiliations":[{"raw_affiliation_string":"University of Kiel,","institution_ids":["https://openalex.org/I32021983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082812594"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.9576,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77579946,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/feature-selection","display_name":"Feature selection","score":0.6588369011878967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6415625214576721},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.627275824546814},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6092081665992737},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5708213448524475},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5649551153182983},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.5436010956764221},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.534356951713562},{"id":"https://openalex.org/keywords/stepwise-regression","display_name":"Stepwise regression","score":0.4964657425880432},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4828908443450928},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46934235095977783},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4399682283401489},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.43445053696632385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4341815412044525},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4306359887123108},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42664653062820435},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4254331886768341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4251742362976074},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42334604263305664},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4197543263435364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22812646627426147},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1761932373046875}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6588369011878967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6415625214576721},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.627275824546814},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6092081665992737},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5708213448524475},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5649551153182983},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.5436010956764221},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.534356951713562},{"id":"https://openalex.org/C170964787","wikidata":"https://www.wikidata.org/wiki/Q7611170","display_name":"Stepwise regression","level":2,"score":0.4964657425880432},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4828908443450928},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46934235095977783},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4399682283401489},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.43445053696632385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4341815412044525},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4306359887123108},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42664653062820435},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4254331886768341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251742362976074},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42334604263305664},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4197543263435364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22812646627426147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1761932373046875},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-105","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W190437827","https://openalex.org/W624668309","https://openalex.org/W1257499219","https://openalex.org/W1480376833","https://openalex.org/W1545302199","https://openalex.org/W1589017226","https://openalex.org/W1967084714","https://openalex.org/W1996716433","https://openalex.org/W2099331417","https://openalex.org/W2127218421","https://openalex.org/W2153635508","https://openalex.org/W2161920802","https://openalex.org/W2163666741","https://openalex.org/W2170892787","https://openalex.org/W2293077345","https://openalex.org/W2395003304","https://openalex.org/W3217795522"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W1975851543","https://openalex.org/W2611973037","https://openalex.org/W2131825398"],"abstract_inverted_index":{"We":[0,45],"extract":[1],"1495":[2],"speech":[3,25,62],"features":[4,13,102],"from":[5,16],"2":[6],"subjectively":[7],"evaluated":[8],"text-to-speech":[9],"(TTS)":[10],"databases.":[11],"These":[12],"are":[14,85],"extracted":[15],"pitch,":[17],"loudness,":[18],"MFCCs,":[19],"spectrals,":[20],"formants,":[21],"and":[22,75,92,119,155],"intensity.":[23],"The":[24,83,160],"material":[26],"is":[27,112],"synthesized":[28],"using":[29],"up":[30,40],"to":[31,41,56,97,115],"15":[32],"different":[33,43,54],"TTS":[34,50],"systems,":[35],"some":[36],"of":[37,61,101],"them":[38],"with":[39],"8":[42],"voices.":[44],"develop":[46],"quality":[47],"predictors":[48,84],"for":[49,152,157,169,176,183],"signals":[51],"following":[52],"two":[53],"approaches":[55],"handle":[57],"the":[58,98,110,116,132,141,170,174,177,181],"huge":[59],"set":[60],"features:":[63],"a":[64,70,105,128],"three-step":[65],"feature":[66,117,120],"selection":[67,121],"followed":[68],"by":[69],"stepwise":[71],"multiple":[72],"linear":[73],"regression":[74],"an":[76],"approach":[77,130],"based":[78],"on":[79],"support":[80],"vector":[81],"machines.":[82],"cross-validated":[86],"via":[87],"3-fold":[88,142],"cross":[89],"validation":[90],"(CV)":[91],"leave-one-test-out":[93],"(LOTO)":[94],"CV.":[95,159],"Due":[96],"high":[99,149],"number":[100],"we":[103,125,145],"apply":[104],"strict":[106,153],"CV":[107,143,154,164],"method":[108],"where":[109,131],"partitioning":[111,133],"realized":[113],"prior":[114],"scaling":[118],"steps.":[122,139],"In":[123,140],"comparison":[124],"also":[126],"follow":[127],"semi-strict":[129,158],"effectively":[134],"takes":[135],"place":[136],"after":[137],"these":[138],"case":[144],"achieve":[146],"correlations":[147,166],"as":[148,150],".75":[151],".89":[156],"more":[161],"ambitious":[162],"LOTO":[163],"yields":[165],"around":[167],".80":[168],"male":[171],"speakers":[172],"whereas":[173],"results":[175],"female":[178],"voices":[179],"show":[180],"need":[182],"improvement.":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}