{"id":"https://openalex.org/W93108289","doi":"https://doi.org/10.21437/interspeech.2006-326","title":"HMM-based MAP prediction of voiced and unvoiced formant frequencies from noisy MFCC vectors","display_name":"HMM-based MAP prediction of voiced and unvoiced formant frequencies from noisy MFCC vectors","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W93108289","doi":"https://doi.org/10.21437/interspeech.2006-326","mag":"93108289"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/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":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4663,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71612866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1540","last_page":"Tue2A1O.3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9742000102996826,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9581000208854675,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9116148352622986},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8629039525985718},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8528419137001038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.745137631893158},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6843556761741638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6732550263404846},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6668742299079895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48014160990715027},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4785638153553009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4306762218475342},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2547151446342468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22931617498397827},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.20921504497528076},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06095963716506958}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.9116148352622986},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8629039525985718},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8528419137001038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.745137631893158},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6843556761741638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6732550263404846},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6668742299079895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48014160990715027},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4785638153553009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4306762218475342},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2547151446342468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22931617498397827},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.20921504497528076},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06095963716506958},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2006-326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:22475","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/22475/","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2394579548","https://openalex.org/W2018086531","https://openalex.org/W2005300405","https://openalex.org/W1980297060","https://openalex.org/W2019183077"],"abstract_inverted_index":{"This":[0,114],"paper":[1],"describes":[2],"how":[3],"formant":[4,48,77,121],"frequencies":[5,78,97,122],"of":[6,45,67,70,73,86,117],"voiced":[7,101],"and":[8,47,61,102,120],"unvoiced":[9,60,91,103],"speech":[10,57,88,104,118],"can":[11],"be":[12],"predicted":[13,99],"from":[14,79,100],"mel-frequency":[15],"cepstral":[16],"coefficients":[17],"(MFCC)":[18],"vectors":[19],"using":[20,58,105,110],"maximum":[21],"a":[22,27,71,80,84,106,126],"posteriori":[23],"(MAP)":[24],"estimation":[25,108],"within":[26],"hidden":[28],"Markov":[29],"model":[30,40,69],"(HMM)":[31],"framework.":[32],"Gaussian":[33],"mixture":[34],"models":[35],"(GMMs)":[36],"are":[37,98],"used":[38],"to":[39],"the":[41,87,111],"local":[42],"joint":[43],"density":[44],"MFCCs":[46],"frequencies.":[49],"More":[50],"localised":[51],"prediction":[52,85,116],"is":[53,94],"achieved":[54],"by":[55],"modelling":[56],"voiced,":[59],"non-speech":[62],"GMMs":[63],"for":[64],"every":[65],"state":[66],"each":[68],"set":[72],"HMMs.":[74],"To":[75],"predict":[76],"MFCC":[81],"vector,":[82],"first":[83],"class":[89,119],"(voiced,":[90],"or":[92],"non-speech)":[93],"made.":[95],"Formant":[96],"MAP":[107],"made":[109],"state-specific":[112],"GMMs.":[113],"'eHMM-GMM'":[115],"was":[123],"evaluated":[124],"on":[125],"male":[127],"5000":[128],"word":[129],"unconstrained":[130],"large":[131],"vocabulary":[132],"speaker-independent":[133],"database.":[134]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}