{"id":"https://openalex.org/W2011224630","doi":"https://doi.org/10.1109/iscslp.2014.6936618","title":"Fusion of magnitude and phase-based features for objective evaluation of TTS voice","display_name":"Fusion of magnitude and phase-based features for objective evaluation of TTS voice","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2011224630","doi":"https://doi.org/10.1109/iscslp.2014.6936618","mag":"2011224630"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","[Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar-382007, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"[Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar-382007, India]","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","[Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar-382007, India]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"[Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar-382007, India]","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.2068,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.45140296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2012","issue":null,"first_page":"521","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8704050779342651},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6782488822937012},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6025269031524658},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.6011962294578552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5785744190216064},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5571204423904419},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49063387513160706},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.48474904894828796},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.4791352450847626},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.466680645942688},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.4466637074947357},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4120134711265564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4030362665653229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39087268710136414},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34728479385375977},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1953655183315277},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19445759057998657},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17628070712089539}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8704050779342651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6782488822937012},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6025269031524658},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.6011962294578552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5785744190216064},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5571204423904419},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49063387513160706},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.48474904894828796},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.4791352450847626},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.466680645942688},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.4466637074947357},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4120134711265564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4030362665653229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39087268710136414},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34728479385375977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1953655183315277},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19445759057998657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17628070712089539},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322211","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W70888257","https://openalex.org/W1257499219","https://openalex.org/W1520853954","https://openalex.org/W1967084714","https://openalex.org/W1981457580","https://openalex.org/W2058673852","https://openalex.org/W2107860279","https://openalex.org/W2118566939","https://openalex.org/W2119125873","https://openalex.org/W2128160875","https://openalex.org/W2141710098","https://openalex.org/W2145212718","https://openalex.org/W2148154194","https://openalex.org/W2163666741","https://openalex.org/W2171903461","https://openalex.org/W2395003304","https://openalex.org/W2404464075","https://openalex.org/W2577886607","https://openalex.org/W2915960560","https://openalex.org/W2917245127","https://openalex.org/W4395692529","https://openalex.org/W4395962115","https://openalex.org/W6677973343","https://openalex.org/W6713425779","https://openalex.org/W6864822029","https://openalex.org/W6865630430"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W2335896301","https://openalex.org/W2012393389","https://openalex.org/W2333240621","https://openalex.org/W2137764249","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W3006618853","https://openalex.org/W2154472250"],"abstract_inverted_index":{"This":[0],"paper":[1],"analyzes":[2],"the":[3,36],"distance-based":[4,171],"objective":[5,17,48,53,82,158,186],"measures":[6,49,83,159,172,187],"for":[7,84,141,157,188],"evaluation":[8,27,42],"of":[9,26,28,31,35,40,47,81,87,117,135,154,191],"Text-to-Speech":[10],"(TTS)":[11],"systems":[12],"(which":[13],"is":[14,50,61],"generally":[15],"used":[16,62,68,161],"measures).":[18],"In":[19,90],"this":[20,64,130],"paper,":[21],"we":[22,132],"discuss":[23],"some":[24],"aspects":[25],"speech":[29],"quality":[30,86,190],"synthesized":[32],"speech.":[33],"Some":[34],"limitations":[37],"and":[38,45,70,98,119,139,146,182],"issues":[39],"subjective":[41,112],"are":[43],"discussed":[44],"importance":[46],"presented.":[51],"Traditional":[52],"measure":[54],"using":[55],"Dynamic":[56],"Time":[57],"Warping":[58],"(DTW)":[59],"distance":[60],"in":[63],"work.":[65],"We":[66],"have":[67,107],"magnitude":[69],"phase-based":[71,99,155],"features":[72,77,97,156],"as":[73,75],"well":[74,177],"auditory":[76],"to":[78],"check":[79],"effectiveness":[80],"predicting":[85],"TTS":[88,192],"voice.":[89,193],"particular,":[91],"Mel":[92],"Frequency":[93],"Cepstral":[94,103],"Coefficients":[95,104],"(MFCC)":[96],"Modified":[100],"Group":[101],"Delay-based":[102],"(MGDCC)":[105],"alone":[106],"no":[108],"good":[109],"correlation":[110,123,136],"with":[111,163,178],"scores.":[113],"However,":[114],"feature-level":[115],"fusion":[116],"MFCC":[118],"MGDCC":[120],"gives":[121],"better":[122],"than":[124],"all":[125],"other":[126],"feature":[127],"sets.":[128],"With":[129],"fusion,":[131],"obtained":[133],"value":[134],"coefficient,":[137],"-0.3":[138],"-0.32":[140],"Blizzard":[142,179],"Challenge":[143,180],"databases":[144,181],"2010":[145],"2011,":[147],"respectively.":[148],"The":[149,166],"results":[150,168],"also":[151],"show":[152,169],"significance":[153],"when":[160],"along":[162],"magnitude-based":[164],"features.":[165],"experimental":[167],"that":[170],"still":[173],"do":[174],"not":[175],"work":[176],"need":[183],"more":[184],"general":[185],"measuring":[189]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}