{"id":"https://openalex.org/W2396731849","doi":"https://doi.org/10.21437/interspeech.2011-568","title":"Automatically creating a diphone set from a speech database","display_name":"Automatically creating a diphone set from a speech database","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2396731849","doi":"https://doi.org/10.21437/interspeech.2011-568","mag":"2396731849"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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 Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","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 Z\u00fcrich"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32389397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2169","last_page":"2172"},"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/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":0.9980000257492065,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.7968403100967407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7851219773292542},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.7850767970085144},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7230187058448792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6234133839607239},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5934484601020813},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5914610028266907},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5861388444900513},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.4676263928413391},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4489228427410126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3527263402938843},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.285006046295166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10850077867507935},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05454230308532715}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7968403100967407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851219773292542},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7850767970085144},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7230187058448792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6234133839607239},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5934484601020813},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5914610028266907},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5861388444900513},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.4676263928413391},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4489228427410126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3527263402938843},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.285006046295166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10850077867507935},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05454230308532715},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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.2011-568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.4946","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.4946","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%3A11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"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":10,"referenced_works":["https://openalex.org/W28591292","https://openalex.org/W88751538","https://openalex.org/W107941679","https://openalex.org/W132122443","https://openalex.org/W170586818","https://openalex.org/W1584787447","https://openalex.org/W1682127088","https://openalex.org/W1733696394","https://openalex.org/W1887401733","https://openalex.org/W2428180336"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W15468680"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,94,99],"measure":[4,13,56,88,108],"that":[5,25,85],"scores":[6],"various":[7],"aspects":[8,39],"of":[9,70,76,81],"phone":[10,18,36,106],"quality.":[11,51],"The":[12,79],"is":[14],"designed":[15],"to":[16,57,92],"penalize":[17],"instances":[19],"with":[20],"one":[21],"or":[22],"several":[23],"characteristics":[24],"are":[26],"not":[27],"desirable":[28],"in":[29],"concatenation-based":[30],"speech":[31,64,100,104],"synthesis.":[32],"Depending":[33],"on":[34],"the":[35,68,86],"type,":[37],"these":[38,71,82],"amongst":[40],"others":[41],"include":[42],"spectrum,":[43],"phase,":[44],"fundamental":[45],"frequency,":[46],"duration,":[47],"voicing":[48],"and":[49,66],"plosive":[50],"We":[52],"applied":[53,91],"this":[54],"quality":[55,69,80,107],"select":[58,93],"diphone":[59,72,96],"sets":[60,73],"from":[61,98],"four":[62],"different":[63],"databases":[65],"demonstrate":[67],"by":[74],"means":[75],"synthesis":[77],"examples.":[78],"examples":[83],"showed":[84],"proposed":[87],"can":[89],"be":[90],"high-quality":[95],"set":[97],"database.":[101],"Index":[102],"Terms:":[103],"synthesis,":[105],"1.":[109]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
