{"id":"https://openalex.org/W2123643019","doi":"https://doi.org/10.1109/icassp.2009.4960567","title":"Efficient gradient F0 tree model for prosody modeling and unit-selection, applied for the embedded US English concatenative TTS","display_name":"Efficient gradient F0 tree model for prosody modeling and unit-selection, applied for the embedded US English concatenative TTS","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2123643019","doi":"https://doi.org/10.1109/icassp.2009.4960567","mag":"2123643019"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/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":true,"raw_author_name":"Slava Shechtman","raw_affiliation_strings":["Haifa Research Laboratory, IBM Research, Haifa, Israel","Haifa Research Lab., IBM Research, Israel"],"affiliations":[{"raw_affiliation_string":"Haifa Research Laboratory, IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"Haifa Research Lab., IBM Research, Israel","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013412274","display_name":"Ryuki Tachibana","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/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Ryuki Tachibana","raw_affiliation_strings":["Tokyo Research Laboratory, IBM Research, Kanagawa, Japan","Tokyo Research Lab., IBM Research, Kanagawa-ken, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Research Laboratory, IBM Research, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"Tokyo Research Lab., IBM Research, Kanagawa-ken, Japan","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035109881"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12411402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":null,"first_page":"4249","last_page":"4252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8790497779846191},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8058766722679138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7356019020080566},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5996502041816711},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5695756077766418},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.549267590045929},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5252268314361572},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5220803618431091},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4886515438556671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4304264783859253},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4197376072406769},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12854638695716858}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8790497779846191},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8058766722679138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7356019020080566},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5996502041816711},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5695756077766418},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.549267590045929},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5252268314361572},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5220803618431091},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4886515438556671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4304264783859253},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4197376072406769},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12854638695716858},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W343569862","https://openalex.org/W1577446345","https://openalex.org/W2102146461","https://openalex.org/W2137851479","https://openalex.org/W2150658333","https://openalex.org/W2154280657","https://openalex.org/W2589083998","https://openalex.org/W2887997480","https://openalex.org/W6611617110","https://openalex.org/W6680019186","https://openalex.org/W6682545244","https://openalex.org/W6734063760"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W4253134045","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3186487487","https://openalex.org/W1489682032"],"abstract_inverted_index":{"Modeling":[0],"of":[1,89],"pitch":[2,8,15],"dynamics":[3],"in":[4,21],"addition":[5],"to":[6,31],"absolute":[7],"modeling":[9],"is":[10],"highly":[11,79],"desirable":[12],"for":[13,36,58,63,81,92,98],"robust":[14],"curve":[16],"prediction":[17],"and":[18,34,38,43,60],"unit":[19],"selection":[20],"concatenative":[22,95],"TTS":[23,83,96],"systems.":[24],"Transition":[25],"prosody":[26],"models":[27],"have":[28],"been":[29],"reported":[30],"improve":[32],"consistency":[33],"naturalness":[35],"pitch-accent":[37],"tonal":[39],"languages,":[40],"like":[41],"Japanese":[42],"Mandarin.":[44],"In":[45],"the":[46],"current":[47],"work":[48],"we":[49],"revise":[50],"a":[51,74],"Gradient":[52],"F0":[53],"tree":[54],"model,":[55],"originally":[56],"developed":[57],"Japanese,":[59],"adjust":[61],"it":[62,78,91],"American":[64,99],"English.":[65,100],"The":[66],"resultant":[67],"model":[68],"requires":[69],"few":[70],"computational":[71],"resources":[72],"at":[73],"runtime":[75],"that":[76],"makes":[77],"suitable":[80],"embedded":[82,94],"applications.":[84],"We":[85],"report":[86],"encouraging":[87],"results":[88],"applying":[90],"an":[93],"system":[97]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}