{"id":"https://openalex.org/W132122443","doi":"https://doi.org/10.21437/interspeech.2009-23","title":"Nearly perfect detection of continuous f_0 contour and frame classification for TTS synthesis","display_name":"Nearly perfect detection of continuous f_0 contour and frame classification for TTS synthesis","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W132122443","doi":"https://doi.org/10.21437/interspeech.2009-23","mag":"132122443"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5018257356","display_name":"Thomas Ewender","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Thomas Ewender","raw_affiliation_strings":["[ETH, Zurich]"],"affiliations":[{"raw_affiliation_string":"[ETH, Zurich]","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020460474","display_name":"Sarah Hoffmann","orcid":"https://orcid.org/0000-0001-9549-2594"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sarah Hoffmann","raw_affiliation_strings":["[ETH, Zurich]"],"affiliations":[{"raw_affiliation_string":"[ETH, Zurich]","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111975528","display_name":"Beat Pfister","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Beat Pfister","raw_affiliation_strings":["[ETH, Zurich]"],"affiliations":[{"raw_affiliation_string":"[ETH, Zurich]","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018257356"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":1.8065,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86654313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7166130542755127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.702284038066864},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6742425560951233},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5678701400756836},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5483657717704773},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.5190868377685547},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4833938181400299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4816526472568512},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45252859592437744},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4512282609939575},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19833365082740784},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05402499437332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166130542755127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.702284038066864},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6742425560951233},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5678701400756836},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5483657717704773},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.5190868377685547},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4833938181400299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4816526472568512},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45252859592437744},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4512282609939575},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19833365082740784},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05402499437332153},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.3825","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.3825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.tik.ee.ethz.ch/~spr/publications/Ewender:09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W198589515","https://openalex.org/W2091425152","https://openalex.org/W2118049600","https://openalex.org/W2394962911","https://openalex.org/W2521776173"],"related_works":["https://openalex.org/W2064065729","https://openalex.org/W2616987818","https://openalex.org/W1890221585","https://openalex.org/W2140156791","https://openalex.org/W3093375612","https://openalex.org/W2127017784","https://openalex.org/W140061127","https://openalex.org/W1506663912","https://openalex.org/W2024201202","https://openalex.org/W2086121913"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,9,18,40,52,64],"new":[3],"method":[4],"for":[5,27],"the":[6,61],"estimation":[7],"of":[8,47,54,63,93],"continuous":[10,41,103],"fundamental":[11,42],"frequency":[12],"(F0)":[13],"contour.":[14],"The":[15,77],"algorithm":[16],"implements":[17],"global":[19],"optimization":[20],"and":[21,75,81,90],"yields":[22],"virtually":[23],"error-free":[24],"F0":[25,33,79,88,104,109],"contours":[26,34],"high":[28],"quality":[29],"speech":[30,56,65,94,99],"signals.":[31],"Such":[32],"are":[35],"subsequently":[36],"used":[37],"to":[38,59,87],"extract":[39],"wave.":[43],"Some":[44],"local":[45],"properties":[46],"this":[48],"wave,":[49],"together":[50],"with":[51],"number":[53],"other":[55],"features":[57],"allow":[58],"classify":[60],"frames":[62],"signal":[66],"into":[67],"five":[68],"classes:":[69],"voiced,":[70],"unvoiced,":[71],"mixed,":[72],"irregularly":[73],"glottalized":[74],"silence.":[76],"presented":[78],"detection":[80],"frame":[82],"classification":[83],"can":[84],"be":[85],"applied":[86],"modeling":[89],"prosodic":[91],"modification":[92],"segments":[95],"in":[96],"high-quality":[97],"concatenative":[98],"synthesis.":[100],"Index":[101],"Terms:":[102],"contour":[105],"estimation,":[106],"globally":[107],"optimized":[108],"contour,":[110],"voiced-unvoiced":[111],"classification,":[112],"irregular":[113]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}