{"id":"https://openalex.org/W972048373","doi":"https://doi.org/10.21437/interspeech.2013-22","title":"Modelling and estimation of the fundamental frequency of speech using a hidden Markov model","display_name":"Modelling and estimation of the fundamental frequency of speech using a hidden Markov model","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W972048373","doi":"https://doi.org/10.21437/interspeech.2013-22","mag":"972048373"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5079749382","display_name":"John Taylor","orcid":"https://orcid.org/0009-0004-9228-3892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. Taylor","raw_affiliation_strings":["Faculty of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":["University of East Anglia, Norwich, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East Anglia, Norwich, United Kingdom","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.01928406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1926","last_page":"1930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9878000020980835,"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":0.9878000020980835,"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":0.9573000073432922,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.868887186050415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7505147457122803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7361457347869873},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6589736342430115},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.651305079460144},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.6144380569458008},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.548738420009613},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48421382904052734},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4754897356033325},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.4638844132423401},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45823031663894653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43245822191238403},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.42421120405197144},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36090290546417236},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.20439466834068298},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19047817587852478},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1861850619316101},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09386032819747925}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.868887186050415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7505147457122803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361457347869873},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6589736342430115},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.651305079460144},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.6144380569458008},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.548738420009613},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48421382904052734},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4754897356033325},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.4638844132423401},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45823031663894653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43245822191238403},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.42421120405197144},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36090290546417236},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.20439466834068298},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19047817587852478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1861850619316101},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09386032819747925},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-22","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-22","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:49381","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/49381/","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":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2535886977","https://openalex.org/W2133857928","https://openalex.org/W2143297499","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905","https://openalex.org/W1843778016"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"using":[3],"a":[4,11,83,105],"hidden":[5],"Markov":[6],"model":[7,10,45,68],"(HMM)":[8],"to":[9,72],"speech":[12,18,27,37,59,84],"signal":[13,85],"in":[14,58],"terms":[15],"of":[16,32,52,100],"its":[17,28],"class":[19,60],"(voiced,":[20],"unvoiced":[21,36],"and":[22,24,38,61,74,86,104],"nonspeech)":[23],"for":[25],"voiced":[26,42],"fundamental":[29,47,64,75],"frequency.":[30],"States":[31],"the":[33,53,62,97,101],"HMM":[34,54],"represent":[35],"nonspeech":[39],"with":[40],"multiple":[41],"states":[43],"that":[44,95],"different":[46],"frequencies.":[48],"The":[49,67],"transition":[50],"matrix":[51],"models":[55],"temporal":[56],"changes":[57],"time-varying":[63],"frequency":[65,76],"contour.":[66],"is":[69,107],"then":[70,87],"applied":[71],"voicing":[73],"estimation":[77,98],"by":[78],"extracting":[79],"acoustic":[80],"features":[81],"from":[82],"applying":[88],"Viterbi":[89],"decoding.":[90],"Experimental":[91],"results":[92],"are":[93],"presented":[94],"investigate":[96],"accuracy":[99],"proposed":[102],"system":[103],"comparison":[106],"made":[108],"against":[109],"conventional":[110],"methods.":[111]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}