{"id":"https://openalex.org/W18378689","doi":"https://doi.org/10.21437/interspeech.2007-548","title":"Iterative unit selection with unnatural prosody detection","display_name":"Iterative unit selection with unnatural prosody detection","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W18378689","doi":"https://doi.org/10.21437/interspeech.2007-548","mag":"18378689"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-548","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5030942871","display_name":"Dacheng Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dacheng Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104229610","display_name":"Min Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Chu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066282713","display_name":"Jieyu Zhao","orcid":"https://orcid.org/0000-0002-1013-557X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jieyu Zhao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030942871"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9659,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8049393,"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":"2909","last_page":"2912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.9637307524681091},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8413288593292236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6593972444534302},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6346067786216736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5641812682151794},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4758020341396332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4700533151626587},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4397607445716858},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3988776206970215},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11859014630317688}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9637307524681091},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8413288593292236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593972444534302},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6346067786216736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5641812682151794},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4758020341396332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4700533151626587},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4397607445716858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3988776206970215},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11859014630317688},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-548","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.3514","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.3514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.ece.gatech.edu/%7Eyzhao33/publications/is2007_AntiProsody.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W75668230","https://openalex.org/W127455173","https://openalex.org/W1887401733","https://openalex.org/W1963846260","https://openalex.org/W2099531983","https://openalex.org/W2106564373","https://openalex.org/W2150658333","https://openalex.org/W2166752834"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W258725851","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W1984347656","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W2108985546"],"abstract_inverted_index":{"Corpus-driven":[0],"speech":[1,134,139],"synthesis":[2,149],"is":[3],"hampered":[4],"by":[5,49,122],"the":[6,13,16,44,50,56,66,87,106,119,128,132],"occurrence":[7],"of":[8,15,71,82],"occasional":[9],"glitches":[10],"which":[11],"ruin":[12],"impression":[14],"whole":[17],"utterance.":[18],"We":[19],"propose":[20],"an":[21,27,40,96],"iterative":[22,148],"unit":[23,141],"selection":[24],"integrated":[25],"with":[26,59],"unnatural":[28,35,51,97,145],"prosody":[29,52,94,98,107,146],"detection":[30,99],"model":[31,53,100,116],"to":[32,92],"identify":[33],"any":[34],"prosody.":[36],"The":[37,114],"system":[38],"searches":[39],"optimal":[41],"path":[42],"in":[43,86,90],"lattice,":[45],"verifies":[46],"its":[47],"naturalness":[48],"and":[54],"replaces":[55],"bad":[57],"section":[58],"a":[60],"better":[61],"candidate,":[62],"until":[63],"it":[64],"passes":[65],"verification":[67],"test.":[68],"In":[69],"light":[70],"hypothesis":[72],"testing,":[73],"we":[74],"show":[75],"this":[76],"trial-and-error":[77],"approach":[78,130],"takes":[79],"effective":[80],"advantage":[81],"abundant":[83],"candidate":[84],"samples":[85],"database.":[88],"Also,":[89],"contrast":[91],"conventional":[93],"prediction,":[95],"still":[101],"leaves":[102],"enough":[103],"room":[104],"for":[105],"variations.":[108],"Unnaturalness":[109],"confidence":[110,143],"measures":[111],"are":[112],"studied.":[113],"combined":[115],"can":[117],"reduce":[118],"objective":[120],"distortion":[121],"16.3%.":[123],"Perceptual":[124],"experiments":[125],"also":[126],"confirm":[127],"proposed":[129],"improves":[131],"synthetic":[133],"quality":[135],"appreciably.":[136],"Index":[137],"Terms:":[138],"synthesis,":[140],"selection,":[142],"measure,":[144],"detection,":[147]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}