{"id":"https://openalex.org/W72468014","doi":"https://doi.org/10.21437/interspeech.2005-174","title":"Fundamental frequency and voicing prediction from MFCCs for speech reconstruction from unconstrained speech","display_name":"Fundamental frequency and voicing prediction from MFCCs for speech reconstruction from unconstrained speech","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W72468014","doi":"https://doi.org/10.21437/interspeech.2005-174","mag":"72468014"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-174","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5102850641","display_name":"Ben Milner","orcid":"https://orcid.org/0000-0001-6315-3475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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/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":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4594,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71815579,"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":"321","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9958999752998352,"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":0.9635000228881836,"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/voice","display_name":"Voice","score":0.8991820812225342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271239757537842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6968356370925903},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4173874258995056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.338034451007843}],"concepts":[{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.8991820812225342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271239757537842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6968356370925903},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4173874258995056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.338034451007843}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2005-174","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.4021","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.4021","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_euro_05.pdf","raw_type":"text"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:22048","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/22048/","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2161269086","https://openalex.org/W3113207934"],"related_works":["https://openalex.org/W1569364549","https://openalex.org/W2981428355","https://openalex.org/W2150288981","https://openalex.org/W1834994814","https://openalex.org/W1599055764","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"This":[0,21],"work":[1],"proposes":[2],"a":[3,13,40,66,84,88,109],"method":[4],"to":[5,33,44,126],"predict":[6,34],"the":[7,31,49,57,94,106,121],"fundamental":[8,35,63,111],"frequency":[9,36,64,112],"and":[10,37,62,87,96],"voicing":[11,38],"of":[12,15,60,93,115],"frame":[14],"speech":[16,27,42,81,98],"from":[17,48],"its":[18],"MFCC":[19,50],"representation.":[20],"has":[22],"particular":[23],"use":[24],"in":[25],"distributed":[26],"recognition":[28],"systems":[29],"where":[30],"ability":[32],"allows":[39],"time-domain":[41],"signal":[43],"be":[45],"reconstructed":[46,95],"solely":[47],"vectors.":[51],"Prediction":[52,75],"is":[53,117],"achieved":[54],"by":[55],"modeling":[56],"joint":[58],"density":[59],"MFCCs":[61],"with":[65],"combined":[67],"hidden":[68],"Markov":[69],"model-Gaussian":[70],"mixture":[71],"model":[72],"(HMM-GMM)":[73],"framework.":[74],"results":[76,103],"are":[77,99],"presented":[78],"on":[79],"unconstrained":[80],"using":[82],"both":[83],"speaker-dependent":[85,107],"database":[86],"speaker-independent":[89,122],"database.":[90],"Spectrogram":[91],"comparisons":[92],"original":[97],"also":[100],"made.":[101],"The":[102],"show":[104],"for":[105,120],"task":[108,123],"percentage":[110],"prediction":[113],"error":[114],"3.1%":[116],"made":[118],"while":[119],"this":[124],"rises":[125],"8.3%.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}