{"id":"https://openalex.org/W2395669661","doi":"https://doi.org/10.21437/interspeech.2015-216","title":"From text to formants \u2014 indirect model for trajectory prediction based on a multi-speaker parallel speech database","display_name":"From text to formants \u2014 indirect model for trajectory prediction based on a multi-speaker parallel speech database","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2395669661","doi":"https://doi.org/10.21437/interspeech.2015-216","mag":"2395669661"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-216","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5007026304","display_name":"K\u00e1lm\u00e1n Abari","orcid":"https://orcid.org/0000-0001-8926-2178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K\u00e1lm\u00e1n Abari","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783073","display_name":"B\u00e1lint T\u00f3th","orcid":"https://orcid.org/0000-0003-1688-9089"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00e1lint P\u00e1l T\u00f3th","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109853981","display_name":"G\u00e1bor Olaszy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00e1bor Olaszy","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19445158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"623","last_page":"627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.9730198383331299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7565070986747742},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.699097752571106},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.656335711479187},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6184699535369873},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5902379751205444},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5162925124168396},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47686681151390076},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43981456756591797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3258577585220337},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.15974140167236328}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.9730198383331299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565070986747742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.699097752571106},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.656335711479187},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6184699535369873},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5902379751205444},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5162925124168396},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47686681151390076},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43981456756591797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3258577585220337},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.15974140167236328},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-216","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W144139046","https://openalex.org/W627498595","https://openalex.org/W1589081167","https://openalex.org/W2000529208","https://openalex.org/W2064758410","https://openalex.org/W2076258817","https://openalex.org/W2092170886","https://openalex.org/W2106610722","https://openalex.org/W2131825398","https://openalex.org/W2213613933","https://openalex.org/W2395775639","https://openalex.org/W2399361930","https://openalex.org/W2400274193","https://openalex.org/W3209383001","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W1975851543","https://openalex.org/W2070163607","https://openalex.org/W2064537740"],"abstract_inverted_index":{"An":[0],"indirect":[1],"model":[2,64,88,102],"is":[3,17,38,65],"presented,":[4],"capable":[5],"of":[6,24,85,112,121],"estimating":[7],"formant":[8,21,60,80,91],"trajectories":[9,92],"from":[10,99],"text":[11],"only":[12],"(Text-to-Formants,":[13],"TTF).":[14],"The":[15,36,63,83,101],"result":[16],"a":[18,68,78,107,118],"phonetically":[19],"correct":[20],"trajectory":[22,81],"flow":[23,111],"any":[25],"virtual":[26],"speech":[27,71],"signal,":[28],"i.e.":[29],"one":[30],"that":[31,90],"has":[32],"never":[33],"been":[34],"uttered.":[35],"focus":[37],"on":[39,58,67],"the":[40,44,50,86,113,122],"pattern":[41],"forms":[42],"inside":[43],"given":[45],"sound,":[46],"taking":[47],"into":[48],"account":[49],"sound":[51],"environment":[52],"(up":[53],"to":[54],"quinphone),":[55],"and":[56,77],"not":[57],"individual":[59],"value":[61],"measurements.":[62],"based":[66],"multi-speaker":[69],"parallel":[70],"database":[72],"with":[73,96],"precise":[74],"manual":[75],"corrections":[76],"HMM-based":[79],"predictor.":[82],"validation":[84],"TTF":[87],"shows":[89],"can":[93],"be":[94],"predicted":[95],"good":[97],"accuracy":[98],"text.":[100],"indirectly":[103],"gives":[104,117],"information":[105],"about":[106],"theoretically":[108],"possible":[109],"articulation":[110],"sentence.":[114],"Thus":[115],"it":[116],"general":[119],"\u2018formantprint\u2019":[120],"language.":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}