{"id":"https://openalex.org/W1931802725","doi":"https://doi.org/10.1109/icassp.2015.7178905","title":"Coherent modification of pitch and energy for expressive prosody implantation","display_name":"Coherent modification of pitch and energy for expressive prosody implantation","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1931802725","doi":"https://doi.org/10.1109/icassp.2015.7178905","mag":"1931802725"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5029658066","display_name":"A. S. Sorin","orcid":"https://orcid.org/0000-0002-9775-2115"},"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":"Alexander Sorin","raw_affiliation_strings":["Speech Technologies, IBM Research-Haifa, Israel","[Speech Technologies, IBM Research - Haifa, Israel]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technologies, IBM Research-Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"[Speech Technologies, IBM Research - Haifa, Israel]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","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":["Speech Technologies, IBM Research-Haifa, Israel","[Speech Technologies, IBM Research - Haifa, Israel]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technologies, IBM Research-Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"[Speech Technologies, IBM Research - Haifa, Israel]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001028439","display_name":"Vincent Pollet","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I4210110200","display_name":"Nuance Communications (Belgium)","ror":"https://ror.org/01zcb7j14","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210110200","https://openalex.org/I4210125787"]}],"countries":["AT","BE"],"is_corresponding":false,"raw_author_name":"Vincent Pollet","raw_affiliation_strings":["Nuance Communications, Text-To-Speech Research, Merelbeke, Belgium","Text-To-Speech Research, Nuance Communications, Merelbeke, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Text-To-Speech Research, Merelbeke, Belgium","institution_ids":["https://openalex.org/I4210110200"]},{"raw_affiliation_string":"Text-To-Speech Research, Nuance Communications, Merelbeke, Belgium","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8699,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73742021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4914","last_page":"4918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6729205250740051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5765624642372131},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.49065887928009033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36238616704940796},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22759857773780823}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6729205250740051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5765624642372131},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.49065887928009033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36238616704940796},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22759857773780823},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W111544860","https://openalex.org/W1528372724","https://openalex.org/W1567986720","https://openalex.org/W1991859832","https://openalex.org/W2101839475","https://openalex.org/W2103783707","https://openalex.org/W2112972560","https://openalex.org/W2155433314","https://openalex.org/W2406189128","https://openalex.org/W4239162268","https://openalex.org/W4248448627"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520","https://openalex.org/W2750037515","https://openalex.org/W4319862652","https://openalex.org/W2394249171"],"abstract_inverted_index":{"In":[0,30],"expressive":[1,9],"TTS":[2],"and":[3,35,59,84,102],"voice":[4],"transformation":[5,109],"systems,":[6],"implantation":[7],"of":[8,26,50,62,88,117],"prosody":[10],"derived":[11],"from":[12],"external":[13],"out-of-domain":[14],"sources":[15],"often":[16],"leads":[17],"to":[18,47,101],"extreme":[19],"pitch":[20,57,71,82,118],"modification":[21,72],"that":[22,39],"compromises":[23],"the":[24,27,40,55,74,81,86,113],"naturalness":[25,41],"synthesized":[28],"speech.":[29],"this":[31,89],"work":[32],"we":[33],"investigate":[34],"prove":[36],"a":[37,48,51,63,92],"hypothesis":[38],"loss":[42],"is":[43,77,99],"in":[44,91],"part":[45],"attributed":[46],"violation":[49],"fundamental":[52],"relationship":[53],"between":[54],"instantaneous":[56,60,75],"frequency":[58,83],"energy":[61,76],"speech":[64],"signal.":[65],"We":[66],"propose":[67],"an":[68],"enhancement":[69],"for":[70,111],"where":[73],"modified":[78],"coherently":[79],"with":[80,106],"demonstrate":[85],"potential":[87],"method":[90],"subjective":[93],"listening":[94],"evaluation.":[95],"The":[96],"proposed":[97],"approach":[98],"complementary":[100],"can":[103],"be":[104],"combined":[105],"spectrum":[107],"shape":[108],"methods":[110],"achieving":[112],"maximal":[114],"possible":[115],"quality":[116],"modification.":[119]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}