{"id":"https://openalex.org/W340328712","doi":"https://doi.org/10.21437/interspeech.2007-245","title":"A comparison of estimated and MAP-predicted formants and fundamental frequencies with a speech reconstruction application","display_name":"A comparison of estimated and MAP-predicted formants and fundamental frequencies with a speech reconstruction application","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W340328712","doi":"https://doi.org/10.21437/interspeech.2007-245","mag":"340328712"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-245","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5063817485","display_name":"Jonathan Darch","orcid":"https://orcid.org/0000-0001-6796-9041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Darch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":["School of Computing Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.651,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6661743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"542","last_page":"545"},"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/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/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":0.9500000476837158},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7450869679450989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7225285172462463},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6518227458000183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6288766860961914},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5507345199584961},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5419249534606934},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.4324500262737274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4293307662010193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4232676029205322},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.4208013415336609},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4148055613040924},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2711678147315979},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.20485609769821167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20115453004837036},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17237421870231628},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14087945222854614},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10903772711753845}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.9500000476837158},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7450869679450989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225285172462463},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6518227458000183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6288766860961914},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5507345199584961},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5419249534606934},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.4324500262737274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4293307662010193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4232676029205322},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.4208013415336609},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4148055613040924},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2711678147315979},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.20485609769821167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20115453004837036},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17237421870231628},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14087945222854614},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10903772711753845},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-245","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1968222399","https://openalex.org/W1979598350","https://openalex.org/W1999885698","https://openalex.org/W2091425152","https://openalex.org/W2106610722","https://openalex.org/W2111593200","https://openalex.org/W2171321863"],"related_works":["https://openalex.org/W2047138445","https://openalex.org/W2044239820","https://openalex.org/W2078307554","https://openalex.org/W24786651","https://openalex.org/W1992686877","https://openalex.org/W146937114","https://openalex.org/W1599045937","https://openalex.org/W2945330824","https://openalex.org/W2007734627","https://openalex.org/W2061239936"],"abstract_inverted_index":{"This":[0],"work":[1],"compares":[2],"the":[3,68,92,123,135],"accuracy":[4,61],"of":[5,57,94,122],"fundamental":[6,26,33,81],"frequency":[7,10,27,34,48,82,103],"and":[8,13,42,50,59,75,116,125],"formant":[9,47],"estimation":[11,28,49,58,83,112,124],"methods":[12,29,52,127],"maximum":[14],"a":[15],"posteriori":[16],"(MAP)":[17],"prediction":[18,35,51,60,64,85,95,104,126],"from":[19,36,65,86,134],"MFCC":[20,37],"vectors":[21,38],"with":[22],"hand-corrected":[23],"references.":[24],"Five":[25],"are":[30,53],"compared":[31],"to":[32,107],"in":[39,113],"both":[40,114],"clean":[41,74,79,115],"noisy":[43,76,117],"speech.":[44,77,118],"Similarly,":[45],"three":[46],"compared.":[54],"An":[55],"analysis":[56,121],"shows":[62],"that":[63],"MFCCs":[66],"provides":[67],"most":[69],"accurate":[70,110],"voicing":[71],"classification":[72],"across":[73],"On":[78],"speech,":[80],"outperforms":[84],"MFCCs,":[87],"but":[88],"as":[89],"noise":[90],"increases":[91],"performance":[93],"is":[96,105,128],"significantly":[97],"more":[98,109],"robust":[99],"than":[100,111],"estimation.":[101],"Formant":[102],"found":[106],"be":[108],"A":[119],"subjective":[120],"also":[129],"made":[130],"by":[131],"reconstructing":[132],"speech":[133],"acoustic":[136],"features.":[137]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}