{"id":"https://openalex.org/W2094519830","doi":"https://doi.org/10.1109/tasl.2010.2040795","title":"Statistical Text-to-Speech Synthesis Based on Segment-Wise Representation With a Norm Constraint","display_name":"Statistical Text-to-Speech Synthesis Based on Segment-Wise Representation With a Norm Constraint","publication_year":2010,"publication_date":"2010-01-22","ids":{"openalex":"https://openalex.org/W2094519830","doi":"https://doi.org/10.1109/tasl.2010.2040795","mag":"2094519830"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2040795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2040795","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5046771851","display_name":"Stas Tiomkin","orcid":"https://orcid.org/0000-0003-3677-6874"},"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"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Stas Tiomkin","raw_affiliation_strings":["Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","Dept. of Electr.Eng., Technion-Israel Inst. of Technol., 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":"Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009813683","display_name":"D. Malah","orcid":"https://orcid.org/0009-0001-8310-7844"},"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"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"David Malah","raw_affiliation_strings":["Department of Electrical Engineering, Technion-Israel Institute of Technology, Haifa, Israel","Dept. of Electr.Eng., Technion-Israel Inst. of Technol., 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":"Dept. of Electr.Eng., Technion-Israel Inst. of Technol., Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035109881","display_name":"Slava Shechtman","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":["IBM Haifa Research Laboratory, Speech Technologies Group, Haifa, Israel","Speech Technol. Group, IBM Haifa Res. Lab., Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Haifa Research Laboratory, Speech Technologies Group, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"Speech Technol. Group, IBM Haifa Res. Lab., Haifa, Israel","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3984,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85280443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"18","issue":"5","first_page":"1077","last_page":"1082"},"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/smoothing","display_name":"Smoothing","score":0.6490557193756104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6282628774642944},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6105750203132629},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5608059167861938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5606691837310791},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.5155208110809326},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4792911410331726},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46565964818000793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4333319664001465},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.426188200712204},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4215099811553955},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.41110140085220337},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37917768955230713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2951444387435913},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1407822072505951},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12229359149932861}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6490557193756104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6282628774642944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6105750203132629},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5608059167861938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5606691837310791},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5155208110809326},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4792911410331726},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46565964818000793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4333319664001465},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.426188200712204},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4215099811553955},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.41110140085220337},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37917768955230713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2951444387435913},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1407822072505951},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12229359149932861},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2040795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2040795","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W75668230","https://openalex.org/W343569862","https://openalex.org/W1514737389","https://openalex.org/W2000513720","https://openalex.org/W2103783707","https://openalex.org/W2125838338","https://openalex.org/W2129142580","https://openalex.org/W2154920538","https://openalex.org/W2183802073","https://openalex.org/W2502265795","https://openalex.org/W2585529150","https://openalex.org/W4285719527","https://openalex.org/W6603100307","https://openalex.org/W6682918086"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"In":[0,48],"statistical":[1],"HMM-based":[2],"text-to-speech":[3],"systems":[4],"(STTS),":[5],"speech":[6,40,80,92,106],"feature":[7,15,27,81,93],"dynamics":[8,28,35],"is":[9],"modeled":[10],"by":[11,61,119],"first-":[12],"and":[13],"second-order":[14],"frame":[16,24,26],"differences,":[17],"which,":[18],"typically,":[19],"do":[20],"not":[21],"satisfactorily":[22],"represent":[23],"to":[25,55,96],"present":[29],"in":[30,37,79,112],"natural":[31,114],"speech.":[32,47],"The":[33,71],"reduced":[34],"results":[36],"over-smoothing":[38],"of":[39,77,87],"features,":[41],"often":[42],"sounding":[43,115],"as":[44,117],"muffled":[45],"synthesized":[46],"this":[49],"correspondence,":[50],"we":[51],"propose":[52],"a":[53,57,63,68,98,102],"method":[54],"enhance":[56],"baseline":[58],"STTS":[59],"system":[60],"introducing":[62],"segment-wise":[64,72],"model":[65],"representation":[66,73],"with":[67],"norm":[69,95,99],"constraint.":[70,100],"provides":[74],"additional":[75],"degrees":[76,86],"freedom":[78,88],"determination.":[82],"We":[83],"exploit":[84],"these":[85],"for":[89],"increasing":[90],"the":[91],"vector":[94],"match":[97],"As":[101],"result,":[103],"statistically":[104],"generated":[105],"features":[107],"are":[108],"less":[109],"over-smoothed,":[110],"resulting":[111],"more":[113],"speech,":[116],"judged":[118],"listening":[120],"tests.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
