{"id":"https://openalex.org/W2116044683","doi":"https://doi.org/10.1109/icassp.2000.859119","title":"Voice quality conversion in TD-PSOLA speech synthesis","display_name":"Voice quality conversion in TD-PSOLA speech synthesis","publication_year":2002,"publication_date":"2002-11-07","ids":{"openalex":"https://openalex.org/W2116044683","doi":"https://doi.org/10.1109/icassp.2000.859119","mag":"2116044683"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2000.859119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2000.859119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","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/A5044683519","display_name":"Xuejing Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xuejing Sun","raw_affiliation_strings":["Speech Acoustics Laboratory Department of Communication Sciences and Disorders, Northwestern University, Evanston, IL, USA","Dept. of Commun. Sci. & Disorders, Northwestern Univ., Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Speech Acoustics Laboratory Department of Communication Sciences and Disorders, Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Dept. of Commun. Sci. & Disorders, Northwestern Univ., Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044683519"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":0.8338,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77625713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"II953","last_page":"II956"},"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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7644789218902588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7418608665466309},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7155307531356812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685263454914093},{"id":"https://openalex.org/keywords/window-function","display_name":"Window function","score":0.5596656203269958},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4448021650314331},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43499165773391724},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3977627456188202},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.16344138979911804}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7644789218902588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7418608665466309},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7155307531356812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685263454914093},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.5596656203269958},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4448021650314331},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43499165773391724},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3977627456188202},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.16344138979911804},{"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:10.1109/icassp.2000.859119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2000.859119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W95551363","https://openalex.org/W1971243715","https://openalex.org/W2022194925","https://openalex.org/W2036340535","https://openalex.org/W2046879791","https://openalex.org/W2051457717","https://openalex.org/W2110420312","https://openalex.org/W2428180336","https://openalex.org/W2900063589","https://openalex.org/W6756398248"],"related_works":["https://openalex.org/W2611973037","https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W1909292483","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"The":[0,117],"capability":[1],"of":[2,28,31],"producing":[3],"different":[4],"voice":[5,48,129],"qualities":[6],"is":[7,44],"highly":[8],"desirable":[9],"in":[10,34,47,114],"modern":[11],"speech":[12],"synthesis":[13,64],"systems.":[14],"Diphone":[15],"based":[16],"synthesizers":[17],"using":[18],"TD-PSOLA":[19,63],"can":[20,125],"generate":[21,126],"high":[22],"quality":[23,49,130],"synthetic":[24],"speech.":[25],"However,":[26],"one":[27],"the":[29,37,41,55,62,69,83,107,127],"drawbacks":[30],"such":[32],"systems":[33],"comparison":[35],"to":[36],"formant":[38],"synthesizer":[39,43],"or":[40],"LPC":[42],"its":[45],"inflexibility":[46],"conversion":[50],"(VQC).":[51],"In":[52],"this":[53,123],"paper,":[54],"author":[56],"presents":[57],"a":[58,74,89,103],"VQC":[59],"method":[60,124],"for":[61,80],"system.":[65],"For":[66],"vocal":[67],"fry,":[68],"ST-signals":[70,84,109],"are":[71,85,110],"multiplied":[72,101],"by":[73,102],"Kaiser":[75],"window":[76],"with":[77,88,95],"alternate":[78],"magnitude;":[79],"breathy":[81],"voice,":[82],"first":[86],"convolved":[87],"one-pole":[90],"filter,":[91],"and":[92,99],"then":[93,111],"combined":[94],"shaped":[96],"noise":[97],"signals,":[98],"finally":[100],"Hanning":[104],"window.":[105],"All":[106],"windowed":[108],"overlap-added":[112],"as":[113],"standard":[115],"TD-PSOLA.":[116],"perceptual":[118],"evaluation":[119],"test":[120],"shows":[121],"that":[122],"desired":[128],"successfully.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}