{"id":"https://openalex.org/W1965568387","doi":"https://doi.org/10.1109/icassp.2013.6638997","title":"Accent Group modeling for improved prosody in statistical parameteric speech synthesis","display_name":"Accent Group modeling for improved prosody in statistical parameteric speech synthesis","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1965568387","doi":"https://doi.org/10.1109/icassp.2013.6638997","mag":"1965568387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gopala Krishna Anumanchipalli","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, US","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, US","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101737161","display_name":"Lu\u00eds Oliveira","orcid":"https://orcid.org/0000-0002-9024-2200"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["PT","US"],"is_corresponding":false,"raw_author_name":"Luis C. Oliveira","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA","L2F Spoken Language Syst. Lab., IST Lisboa, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"L2F Spoken Language Syst. Lab., IST Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W Black","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068922218"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.4596,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92424174,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"6890","last_page":"6894"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/stress","display_name":"Stress (linguistics)","score":0.8203789591789246},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.8060617446899414},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7395622134208679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354164123535156},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6753939986228943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5988981127738953},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5879387259483337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5609221458435059},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5236192345619202},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5145227313041687},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.5075167417526245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5023055076599121},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5012249946594238},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.45737528800964355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15010133385658264},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07641252875328064}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8203789591789246},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.8060617446899414},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7395622134208679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354164123535156},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6753939986228943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5988981127738953},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5879387259483337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5609221458435059},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5236192345619202},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5145227313041687},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.5075167417526245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023055076599121},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5012249946594238},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.45737528800964355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15010133385658264},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07641252875328064},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.7726","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.7726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~gopalakr/publications/agroupspss_icassp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W132904463","https://openalex.org/W202879582","https://openalex.org/W397522103","https://openalex.org/W1492653331","https://openalex.org/W1523135049","https://openalex.org/W1553896573","https://openalex.org/W1567156305","https://openalex.org/W1570629387","https://openalex.org/W1970354675","https://openalex.org/W2000513720","https://openalex.org/W2005465272","https://openalex.org/W2084303973","https://openalex.org/W2093414802","https://openalex.org/W2099352211","https://openalex.org/W2116043656","https://openalex.org/W2129142580","https://openalex.org/W2143777890","https://openalex.org/W2150658333","https://openalex.org/W2154280657","https://openalex.org/W2154920538","https://openalex.org/W2158086337","https://openalex.org/W2167212867","https://openalex.org/W2295027170","https://openalex.org/W2330979245","https://openalex.org/W2400063444","https://openalex.org/W2439178139","https://openalex.org/W2732425225","https://openalex.org/W2916535084","https://openalex.org/W3144792678","https://openalex.org/W4206906090","https://openalex.org/W6634126500","https://openalex.org/W6712610176","https://openalex.org/W7071737483"],"related_works":["https://openalex.org/W4212971584","https://openalex.org/W2088008556","https://openalex.org/W1965454423","https://openalex.org/W2381837697","https://openalex.org/W2474947928","https://openalex.org/W2332932563","https://openalex.org/W2530248338","https://openalex.org/W2967415048","https://openalex.org/W4301230705","https://openalex.org/W1489682032"],"abstract_inverted_index":{"This":[0,67],"paper":[1],"presents":[2],"an":[3,16,44,73],"`Accent":[4],"Group'":[5],"based":[6],"intonation":[7,86],"model":[8,20,47,68,93],"for":[9],"statistical":[10],"parametric":[11],"speech":[12],"synthesis.":[13],"We":[14,42],"propose":[15],"approach":[17],"to":[18,34,49,71],"automatically":[19],"phonetic":[21],"realizations":[22],"of":[23,30,37,51,83,91,102],"fundamental":[24],"frequency(F0)":[25],"contours":[26],"as":[27],"a":[28,35,55,100],"sequence":[29],"intonational":[31],"events":[32],"anchored":[33],"group":[36],"syllables":[38],"(an":[39],"Accent":[40],"Group).":[41],"train":[43],"accent":[45,79],"grouping":[46],"specific":[48],"that":[50],"the":[52,65,92],"speaker,":[53],"using":[54],"stochastic":[56],"context":[57],"free":[58],"grammar":[59],"and":[60,97,110],"contextual":[61],"decision":[62],"trees":[63],"on":[64,99],"syllables.":[66],"is":[69,87,94],"used":[70],"`parse'":[72],"unseen":[74],"text":[75],"into":[76],"its":[77],"constituent":[78],"groups":[80],"over":[81],"each":[82],"which":[84],"appropriate":[85],"predicted.":[88],"The":[89],"performance":[90],"shown":[95],"objectively":[96],"subjectively":[98],"variety":[101],"prosodically":[103],"diverse":[104],"tasks-":[105],"read":[106],"speech,":[107],"news":[108],"broadcast":[109],"audio":[111],"books.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}