{"id":"https://openalex.org/W2295027170","doi":"https://doi.org/10.21437/interspeech.2011-36","title":"A statistical phrase/accent model for intonation modeling","display_name":"A statistical phrase/accent model for intonation modeling","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2295027170","doi":"https://doi.org/10.21437/interspeech.2011-36","mag":"2295027170"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gopala Krishna Anumanchipalli","raw_affiliation_strings":[],"affiliations":[]},{"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/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"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":"Lu\u00eds C. Oliveira","raw_affiliation_strings":["\u2020Spoken Language Systems Laboratory, INESC-ID/IST Lisboa, Portugal 1000-029","\u2021Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA 15213"],"affiliations":[{"raw_affiliation_string":"\u2020Spoken Language Systems Laboratory, INESC-ID/IST Lisboa, Portugal 1000-029","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"\u2021Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"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/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"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":"Alan W. Black","raw_affiliation_strings":["\u2020Spoken Language Systems Laboratory, INESC-ID/IST Lisboa, Portugal 1000-029","\u2021Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA 15213"],"affiliations":[{"raw_affiliation_string":"\u2020Spoken Language Systems Laboratory, INESC-ID/IST Lisboa, Portugal 1000-029","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"\u2021Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA 15213","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":[],"apc_list":null,"apc_paid":null,"fwci":3.9472,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.940534,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1813","last_page":"1816"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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":0.9940999746322632,"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/stress","display_name":"Stress (linguistics)","score":0.8622045516967773},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.8349066972732544},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.7965834140777588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7648686170578003},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7153787612915039},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.668147087097168},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.633380115032196},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6090741753578186},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5639636516571045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.499711275100708},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4727015495300293},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44653382897377014},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.4409584403038025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3843769431114197},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13023951649665833},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1094675362110138},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10414507985115051}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8622045516967773},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8349066972732544},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.7965834140777588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648686170578003},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7153787612915039},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.668147087097168},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.633380115032196},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6090741753578186},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5639636516571045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499711275100708},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4727015495300293},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44653382897377014},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.4409584403038025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3843769431114197},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13023951649665833},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1094675362110138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10414507985115051},{"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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-36","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.208.5075","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.208.5075","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/%7Egopalakr/publications/anumanchipalli_spamf0.PDF","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W162654330","https://openalex.org/W202879582","https://openalex.org/W1500192039","https://openalex.org/W1514737389","https://openalex.org/W1553896573","https://openalex.org/W1567156305","https://openalex.org/W1570629387","https://openalex.org/W1583314545","https://openalex.org/W1990448242","https://openalex.org/W2000513720","https://openalex.org/W2005465272","https://openalex.org/W2093414802","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2154280657"],"related_works":["https://openalex.org/W2381837697","https://openalex.org/W4212971584","https://openalex.org/W2332932563","https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W2052542215","https://openalex.org/W2036564641","https://openalex.org/W49590631"],"abstract_inverted_index":{"This":[0,60],"paper":[1],"proposes":[2],"a":[3],"statistical":[4],"phrase/accent":[5],"model":[6,93],"of":[7,23,56,62,68],"voice":[8],"fundamental":[9],"frequency(F0)":[10],"for":[11,18],"speech":[12,112],"synthesis.":[13],"It":[14],"presents":[15],"an":[16],"approach":[17],"automatic":[19],"extraction":[20],"and":[21,25,65,113],"modeling":[22,63],"phrase":[24],"accent":[26],"phenomena":[27],"from":[28],"F0":[29,58,69,78,100],"contours":[30],"by":[31],"taking":[32],"into":[33],"account":[34],"their":[35],"overall":[36],"trends":[37],"in":[38,81,102],"the":[39,53,57,91],"training":[40],"data.":[41],"An":[42],"iterative":[43],"optimization":[44],"algorithm":[45],"is":[46,71,94],"described":[47],"to":[48,73],"extract":[49],"these":[50],"components,":[51],"minimizing":[52],"reconstruction":[54],"error":[55],"contour.":[59],"method":[61],"local":[64],"global":[66],"components":[67],"separately":[70],"shown":[72],"be":[74],"better":[75,96],"than":[76,97],"conventional":[77],"models":[79,101],"used":[80],"Statistical":[82],"Parametric":[83],"Speech":[84],"Synthesis":[85],"(SPSS).":[86],"Perceptual":[87],"evaluations":[88],"confirm":[89],"that":[90],"proposed":[92],"significantly":[95],"baseline":[98],"SPSS":[99],"3":[103],"prosodically":[104],"diverse":[105],"tasks":[106],"\u2013":[107],"read":[108],"speech,":[109],"radio":[110],"broadcast":[111],"audio":[114],"book":[115],"speech.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}