{"id":"https://openalex.org/W2166366223","doi":"https://doi.org/10.1109/icpr.1994.577142","title":"Speech synthesis for a specific speaker based on a labeled speech database","display_name":"Speech synthesis for a specific speaker based on a labeled speech database","publication_year":2002,"publication_date":"2002-12-17","ids":{"openalex":"https://openalex.org/W2166366223","doi":"https://doi.org/10.1109/icpr.1994.577142","mag":"2166366223"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.1994.577142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.1994.577142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th IAPR International Conference on Pattern Recognition (Cat. No.94CH3440-5)","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/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]},{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"R. Hoory","raw_affiliation_strings":["Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","HRL Audio/Video Technologies group, IBM Israel Science and Technology Center, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"HRL Audio/Video Technologies group, IBM Israel Science and Technology Center, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088164820","display_name":"Daniel Chazan","orcid":"https://orcid.org/0000-0002-3593-8483"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"D. Chazan","raw_affiliation_strings":["HRL Audio/Video Technologies group, IBM Israel Science and Technology Center, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HRL Audio/Video Technologies group, IBM Israel Science and Technology Center, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9941999912261963,"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":0.9941999912261963,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9642000198364258,"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/computer-science","display_name":"Computer science","score":0.8133969306945801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7526788711547852},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6603396534919739},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.6127926707267761},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5904127955436707},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5585943460464478},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5421667098999023},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.529634952545166},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4910123646259308},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.45826560258865356},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.41914311051368713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3495316505432129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133969306945801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7526788711547852},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6603396534919739},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.6127926707267761},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5904127955436707},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5585943460464478},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5421667098999023},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.529634952545166},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4910123646259308},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.45826560258865356},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.41914311051368713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3495316505432129}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.1994.577142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.1994.577142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th IAPR International Conference on Pattern Recognition (Cat. No.94CH3440-5)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1890221585","https://openalex.org/W1949964979","https://openalex.org/W1982496939","https://openalex.org/W2014195737","https://openalex.org/W2059450962","https://openalex.org/W2083205780","https://openalex.org/W2107451257","https://openalex.org/W2141001554","https://openalex.org/W2160741249","https://openalex.org/W2493732675"],"related_works":["https://openalex.org/W2159307410","https://openalex.org/W2163834050","https://openalex.org/W2120076107","https://openalex.org/W137020845","https://openalex.org/W1999835922","https://openalex.org/W1542588102","https://openalex.org/W2020464095","https://openalex.org/W4319347033","https://openalex.org/W2151333624","https://openalex.org/W2131711534"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,15,29,39,43,67],"new":[4],"text-to-speech":[5],"synthesis":[6,19],"technique,":[7],"for":[8],"producing":[9],"continuous,":[10],"natural":[11,69,121],"sounding":[12],"speech":[13,26,31,59,74,105,114],"of":[14,38,86,123],"specific":[16],"speaker.":[17,125],"The":[18,33,47,111],"technique":[20],"is":[21,50,76,116],"based":[22],"on":[23],"selecting":[24],"short":[25],"frames":[27],"from":[28],"phoneme-labeled":[30],"database.":[32],"selection":[34],"procedure":[35],"involves":[36],"minimization":[37],"distortion":[40],"criterion,":[41],"by":[42,102],"dynamic":[44],"programming":[45],"algorithm.":[46],"proposed":[48],"scheme":[49],"more":[51,68],"flexible":[52],"than":[53],"many":[54],"existing":[55],"schemes":[56],"using":[57],"fixed":[58],"segments,":[60],"such":[61],"as":[62],"diphones.":[63],"It":[64],"results":[65],"in":[66,91,97],"synthesized":[70,113],"speech.":[71,87],"An":[72],"efficient":[73],"representation":[75],"used":[77],"to":[78],"express":[79],"simply":[80],"and":[81,96,109,118],"accurately":[82],"the":[83,92,104,120,124],"spectral":[84],"continuity":[85],"A":[88],"further":[89],"improvement":[90],"database":[93,98],"search":[94],"mechanism":[95],"size":[99],"was":[100],"obtained":[101],"sectioning":[103],"phonemes":[106],"into":[107],"\"steady-states\"":[108],"\"transitions\".":[110],"resulting":[112],"quality,":[115],"satisfactory":[117],"preserves":[119],"voice":[122]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}