{"id":"https://openalex.org/W1500927682","doi":"https://doi.org/10.21437/eurospeech.1997-20","title":"Creating unseen triphones by phone concatenation in the spectral, cepstral and formant domains","display_name":"Creating unseen triphones by phone concatenation in the spectral, cepstral and formant domains","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W1500927682","doi":"https://doi.org/10.21437/eurospeech.1997-20","mag":"1500927682"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5111720093","display_name":"Mats Blomberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mats Blomberg","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5111720093"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4266,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62914512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1187","last_page":"1190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.952305018901825},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.896843433380127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6985973715782166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5945411324501038},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5157642364501953},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5152402520179749},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4850012958049774},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4698202908039093},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4479564428329468},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4316464066505432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42514902353286743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.333243191242218},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33224189281463623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2264370322227478},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.158010333776474},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10123339295387268},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.075306236743927}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.952305018901825},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.896843433380127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985973715782166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5945411324501038},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5157642364501953},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5152402520179749},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4850012958049774},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4698202908039093},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4479564428329468},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4316464066505432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42514902353286743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.333243191242218},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33224189281463623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2264370322227478},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.158010333776474},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10123339295387268},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.075306236743927},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.1997-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.7952","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.7952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.kth.se/ctt/publications/papers/ES97_1187.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.3921","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.3921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ling.umu.se/pub/phonum/phonum4/41.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W1558503095"],"related_works":["https://openalex.org/W2368661496","https://openalex.org/W2380156283","https://openalex.org/W2085241361","https://openalex.org/W2018337942","https://openalex.org/W2137133401","https://openalex.org/W2888091758","https://openalex.org/W2394579548","https://openalex.org/W2018086531","https://openalex.org/W2005300405","https://openalex.org/W2134209752"],"abstract_inverted_index":{"A":[0,96],"technique":[1,43,102],"for":[2,51,60,80,105],"predicting":[3],"triphones":[4,70],"by":[5,88],"concatenation":[6],"of":[7,23,30,48,67,111],"diphone":[8],"or":[9],"monophone":[10],"models":[11,15],"is":[12,71,83,103],"studied.":[13],"The":[14,41,64],"are":[16,33,58],"connected":[17],"using":[18],"linear":[19,25],"interpolation":[20],"between":[21],"endpoints":[22],"piece-wise":[24],"parameter":[26],"trajectories.":[27],"Three":[28],"types":[29],"spectral":[31,46],"representation":[32],"compared:":[34],"formants,":[35],"filter":[36,75],"amplitudes":[37],"and":[38,62,76],"cepstmm":[39,77],"coefficients.":[40],"proposed":[42,101],"lowers":[44],"the":[45,49,68,74,91,100,109],"distortion":[47],"phones":[50],"all":[52,106],"three":[53],"representations":[54,107],"when":[55],"different":[56],"speakers":[57],"used":[59],"training":[61],"evaluation.":[63],"average":[65],"error":[66],"created":[69],"lower":[72],"in":[73,90,108],"domains":[78],"than":[79],"formants.":[81],"This":[82],"explained":[84],"to":[85],"be":[86],"caused":[87],"limitations":[89],"Analysis-bySynthesis":[92],"formant":[93],"tracking":[94],"algorithm.":[95],"small":[97],"improvement":[98],"with":[99],"achieved":[104],"task":[110],"reordering":[112],"N-best":[113],"sentence":[114],"recognition":[115],"candidate":[116],"lists.":[117]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
