{"id":"https://openalex.org/W2068603351","doi":"https://doi.org/10.1109/asru.2011.6163946","title":"Automatic detection of unnatural word-level segments in unit-selection speech synthesis","display_name":"Automatic detection of unnatural word-level segments in unit-selection speech synthesis","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2068603351","doi":"https://doi.org/10.1109/asru.2011.6163946","mag":"2068603351"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2011.6163946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","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/A5100702485","display_name":"William Yang Wang","orcid":"https://orcid.org/0000-0001-6153-8240"},"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"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Yang Wang","raw_affiliation_strings":["Computer Science Department, Columbia University, New York, NY, USA","School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112401163","display_name":"Kallirroi Georgila","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kallirroi Georgila","raw_affiliation_strings":["Institute for Creative Technologies, University of Southern California, Playa Vista, CA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Creative Technologies, University of Southern California, Playa Vista, CA, USA","institution_ids":["https://openalex.org/I4210087747","https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100702485"],"corresponding_institution_ids":["https://openalex.org/I74973139","https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.8805,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80330284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"22","issue":null,"first_page":"289","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","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/crfs","display_name":"CRFS","score":0.7997786402702332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7931795120239258},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.710104763507843},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6121581792831421},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6102368831634521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.601126492023468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5983188152313232},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5006592273712158},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4932181239128113},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4893788695335388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46955540776252747},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.4388638734817505},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.43387770652770996},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4268919825553894},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4241047501564026},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4165743589401245},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10474896430969238}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.7997786402702332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931795120239258},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.710104763507843},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6121581792831421},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6102368831634521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.601126492023468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5983188152313232},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5006592273712158},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4932181239128113},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4893788695335388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46955540776252747},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.4388638734817505},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.43387770652770996},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4268919825553894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4241047501564026},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4165743589401245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10474896430969238},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":2,"locations":[{"id":"doi:10.1109/asru.2011.6163946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.6008","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.6008","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/%7Eyww/papers/asru2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W93128823","https://openalex.org/W159401140","https://openalex.org/W179658191","https://openalex.org/W228314209","https://openalex.org/W1833445864","https://openalex.org/W1920532145","https://openalex.org/W2008834750","https://openalex.org/W2029996593","https://openalex.org/W2091359957","https://openalex.org/W2135731857","https://openalex.org/W2136945651","https://openalex.org/W2153804780","https://openalex.org/W6603767190","https://openalex.org/W6638612908","https://openalex.org/W6640459522","https://openalex.org/W6680340802","https://openalex.org/W6680393613","https://openalex.org/W6682780409"],"related_works":["https://openalex.org/W2055466819","https://openalex.org/W50079190","https://openalex.org/W2356597680","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W2577088515","https://openalex.org/W2370711060"],"abstract_inverted_index":{"We":[0,15,54,73],"investigate":[1],"the":[2],"problem":[3],"of":[4,20],"automatically":[5],"detecting":[6],"unnatural":[7],"word-level":[8],"segments":[9],"in":[10],"unit":[11],"selection":[12],"speech":[13],"synthesis.":[14],"use":[16],"a":[17,80],"large":[18],"set":[19],"features,":[21],"namely,":[22],"target":[23],"and":[24,32,34,42,51,68,78],"join":[25],"costs,":[26],"language":[27],"models,":[28],"prosodic":[29],"cues,":[30],"energy":[31],"spectrum,":[33],"Delta":[35],"Term":[36],"Frequency":[37,40],"Inverse":[38],"Document":[39],"(TF-IDF),":[41],"we":[43],"report":[44],"comparative":[45],"results":[46,77],"between":[47],"different":[48],"feature":[49],"types":[50],"their":[52],"combinations.":[53],"also":[55],"compare":[56],"three":[57],"modeling":[58],"methods":[59],"based":[60],"on":[61],"Support":[62],"Vector":[63],"Machines":[64],"(SVMs),":[65],"Random":[66,70],"Forests,":[67],"Conditional":[69],"Fields":[71],"(CRFs).":[72],"then":[74],"discuss":[75],"our":[76],"present":[79],"comprehensive":[81],"error":[82],"analysis.":[83]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
