{"id":"https://openalex.org/W19839536","doi":"https://doi.org/10.21437/interspeech.2005-621","title":"Discontinuity detection in concatenated speech synthesis based on nonlinear speech analysis","display_name":"Discontinuity detection in concatenated speech synthesis based on nonlinear speech analysis","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W19839536","doi":"https://doi.org/10.21437/interspeech.2005-621","mag":"19839536"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-621","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010084334","display_name":"Yannis Pantazis","orcid":"https://orcid.org/0000-0002-2009-7562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Pantazis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109914325","display_name":"Esther Klabbers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esther Klabbers","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7428,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.674155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2817","last_page":"2820"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9983000159263611,"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/discontinuity","display_name":"Discontinuity (linguistics)","score":0.7621798515319824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7085063457489014},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6509467363357544},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6167377233505249},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5779876708984375},{"id":"https://openalex.org/keywords/demodulation","display_name":"Demodulation","score":0.5578159093856812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.556006669998169},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5332037806510925},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4520357847213745},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.430172860622406},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42567145824432373},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4219118654727936},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34197062253952026},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3242759108543396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3240954279899597},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1956247091293335},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09723228216171265},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0920223593711853}],"concepts":[{"id":"https://openalex.org/C2777042112","wikidata":"https://www.wikidata.org/wiki/Q5281658","display_name":"Discontinuity (linguistics)","level":2,"score":0.7621798515319824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7085063457489014},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6509467363357544},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6167377233505249},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5779876708984375},{"id":"https://openalex.org/C195251586","wikidata":"https://www.wikidata.org/wiki/Q1185939","display_name":"Demodulation","level":3,"score":0.5578159093856812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.556006669998169},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5332037806510925},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4520357847213745},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.430172860622406},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42567145824432373},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4219118654727936},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34197062253952026},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3242759108543396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3240954279899597},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1956247091293335},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09723228216171265},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0920223593711853},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2005-621","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.217.1272","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.1272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.bme.ogi.edu/~klabbers/papers/IS051061.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W60941773","https://openalex.org/W95551363","https://openalex.org/W116305788","https://openalex.org/W1493929315","https://openalex.org/W1538482441","https://openalex.org/W1550297032","https://openalex.org/W1584787447","https://openalex.org/W1733696394","https://openalex.org/W1887401733","https://openalex.org/W1999016813","https://openalex.org/W2032038440","https://openalex.org/W2033010331","https://openalex.org/W2068804781","https://openalex.org/W2150658333","https://openalex.org/W2406491574","https://openalex.org/W2799061466"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1546240199","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1984921740","https://openalex.org/W193702574","https://openalex.org/W642007152","https://openalex.org/W2154415461","https://openalex.org/W596245619","https://openalex.org/W2056066842"],"abstract_inverted_index":{"An":[0],"objective":[1],"distance":[2],"measure":[3],"which":[4,118],"is":[5,16,50,63,119],"able":[6],"to":[7],"predict":[8],"audible":[9,93],"discontinuity":[10,94],"in":[11,70],"concatenated":[12],"speech":[13,58,69],"synthesis":[14],"systems":[15],"very":[17],"important.":[18],"Previous":[19],"works":[20],"were":[21],"primarily":[22],"based":[23,51,64],"on":[24,52,65,128],"features":[25],"estimated":[26],"by":[27],"linear":[28,83,108],"and/or":[29],"stationary":[30],"models":[31],"of":[32,45,57,68,90,113],"speech.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,101],"introduce":[38],"two":[39,104],"nonlinear":[40,54],"approaches":[41],"for":[42,87],"the":[43,60,66,78,88,103,129],"detection":[44,111],"discontinuity.":[46],"The":[47],"first":[48],"method":[49,62],"a":[53,74,110],"harmonic":[55],"model":[56],"while":[59],"second":[61],"demodulation":[67],"an":[71,120],"amplitude":[72],"and":[73],"frequency":[75],"component":[76],"using":[77,106],"Teager":[79],"energy":[80],"operator.":[81],"Fisher\u2019s":[82,107],"discriminant":[84,109],"was":[85,116],"used":[86],"separation":[89],"signals":[91],"with":[92],"from":[95],"those":[96],"perceived":[97],"as":[98],"continuous.":[99],"When":[100],"combined":[102],"methods":[105],"rate":[112],"56.5":[114],"%":[115,122],"achieved":[117],"90":[121],"improvement":[123],"over":[124],"previously":[125],"published":[126],"results":[127],"same":[130],"database.":[131],"1.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}