{"id":"https://openalex.org/W107941679","doi":"https://doi.org/10.21437/interspeech.2010-79","title":"Accurate pitch marking for prosodic modification of speech segments","display_name":"Accurate pitch marking for prosodic modification of speech segments","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W107941679","doi":"https://doi.org/10.21437/interspeech.2010-79","mag":"107941679"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-79","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-79","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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":"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":2,"corresponding_author_ids":["https://openalex.org/A5018257356"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":1.3965,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83589294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"181"},"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":0.9991000294685364,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9972000122070312,"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/pitch-contour","display_name":"Pitch contour","score":0.7482190132141113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271052598953247},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.7085649967193604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6920640468597412},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.572111189365387},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.553541362285614},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5204160809516907},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5081565380096436},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4297217130661011},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4248330295085907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32209083437919617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1280367076396942}],"concepts":[{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.7482190132141113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271052598953247},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.7085649967193604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6920640468597412},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.572111189365387},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.553541362285614},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5204160809516907},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5081565380096436},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4297217130661011},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4248330295085907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32209083437919617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1280367076396942},{"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/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.2010-79","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-79","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.8502","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.8502","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%3A10.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":9,"referenced_works":["https://openalex.org/W63768818","https://openalex.org/W132122443","https://openalex.org/W1535042324","https://openalex.org/W1544887551","https://openalex.org/W1875231349","https://openalex.org/W1985282389","https://openalex.org/W2054586990","https://openalex.org/W2394962911","https://openalex.org/W2583817739"],"related_works":["https://openalex.org/W2117854015","https://openalex.org/W2044564457","https://openalex.org/W1548784694","https://openalex.org/W2111139066","https://openalex.org/W1948499687","https://openalex.org/W2149528081","https://openalex.org/W2387387595","https://openalex.org/W2349264490","https://openalex.org/W284503395","https://openalex.org/W2164147372"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,41,71,99],"new":[4],"approach":[5],"to":[6,35,56,65],"pitch":[7,48,87,116,119],"marking.":[8,49],"Unlike":[9],"other":[10],"approaches":[11],"that":[12,84,103],"use":[13,40],"the":[14,20,27,51,66,85,92],"same":[15],"combination":[16,76],"of":[17,44,94],"features":[18,33],"for":[19,47,106],"whole":[21],"signal,":[22],"we":[23,39,63],"take":[24],"into":[25],"account":[26],"signal":[28,121],"properties":[29],"and":[30],"apply":[31],"different":[32],"according":[34],"some":[36],"heuristic.":[37],"Basically":[38],"special":[42],"type":[43],"energy":[45,52],"contour":[46,74],"Where":[50],"information":[53],"turns":[54],"out":[55],"be":[57],"not":[58],"suitable":[59],"as":[60],"an":[61],"indicator":[62],"resort":[64],"fundamental":[67],"wave":[68],"computed":[69],"from":[70],"contiguous":[72],"F0":[73],"in":[75],"with":[77],"detailed":[78],"voicing":[79],"information.":[80],"Our":[81],"experiments":[82],"demonstrate":[83],"proposed":[86],"marking":[88],"algorithm":[89],"clearly":[90],"improves":[91],"quality":[93],"synthesised":[95],"speech":[96,111],"generated":[97],"by":[98],"concatenative":[100],"text-to-speech":[101],"system":[102],"uses":[104],"TD-PSOLA":[105],"prosodic":[107],"modifications.":[108],"Index":[109],"Terms:":[110],"synthesis,":[112],"glottal":[113],"closure":[114],"instants,":[115],"marks,":[117],"automatic":[118],"marking,":[120],"analysis.":[122]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}