{"id":"https://openalex.org/W1506033385","doi":"https://doi.org/10.21437/interspeech.2004-389","title":"MAP prediction of pitch from MFCC vectors for speech reconstruction","display_name":"MAP prediction of pitch from MFCC vectors for speech reconstruction","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W1506033385","doi":"https://doi.org/10.21437/interspeech.2004-389","mag":"1506033385"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-389","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5110379443","display_name":"Xu Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Shao","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 P. Milner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2867,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.53393996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2425","last_page":"2428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.872523307800293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7192603945732117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6964207887649536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46835771203041077},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.41930124163627625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39961761236190796},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2835075855255127}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.872523307800293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192603945732117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6964207887649536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46835771203041077},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.41930124163627625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39961761236190796},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2835075855255127}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2004-389","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.62.5635","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.62.5635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~xu/download/sx_icslp_04.pdf","raw_type":"text"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:3053","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/3053/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W126257978","https://openalex.org/W1493898446","https://openalex.org/W1528372724","https://openalex.org/W1543669765","https://openalex.org/W2161269086","https://openalex.org/W3113207934"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2736574136","https://openalex.org/W2373675101","https://openalex.org/W2038216521","https://openalex.org/W106160982","https://openalex.org/W894828327","https://openalex.org/W2136559180"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"a":[3,18,37,56,92,127],"method":[4,45],"of":[5,30,51,71,96,104],"predicting":[6],"pitch":[7,35,53,78,102,108],"and":[8,34,99],"voicing":[9,93],"from":[10,82,123],"mel-frequency":[11],"cepstral":[12],"coefficient":[13],"(MFCC)":[14],"vectors.":[15],"Two":[16],"maximum":[17],"posteriori":[19],"(MAP)":[20],"methods":[21],"are":[22,65],"considered.":[23],"The":[24,106],"first":[25],"models":[26,47],"the":[27,31,43,48,52,69,118],"joint":[28],"distribution":[29],"MFCC":[32,89],"vector":[33],"using":[36,55,126],"Gaussian":[38],"mixture":[39],"model":[40,60],"(GMM)":[41],"while":[42],"second":[44],"also":[46,111],"temporal":[49],"correlation":[50],"contour":[54,109],"combined":[57],"hidden":[58],"Markov":[59],"(HMM)-GMM":[61],"framework.":[62],"Monophone-based":[63],"HMMs":[64],"connected":[66],"together":[67],"in":[68],"form":[70],"an":[72,100],"unconstrained":[73,83],"monophone":[74],"grammar":[75],"which":[76],"enables":[77],"to":[79,113],"be":[80],"predicted":[81,107],"speech":[84,115,120],"input.":[85],"Evaluation":[86],"on":[87],"130,000":[88],"vectors":[90],"reveals":[91],"classification":[94],"accuracy":[95],"over":[97],"92%":[98],"RMS":[101],"error":[103],"10Hz.":[105],"is":[110],"applied":[112],"MFCC-based":[114],"reconstruction":[116],"with":[117],"resultant":[119],"almost":[121],"indistinguishable":[122],"that":[124],"reconstructed":[125],"reference":[128],"pitch.":[129],"1.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}