{"id":"https://openalex.org/W2006051038","doi":"https://doi.org/10.1109/tasl.2010.2047811","title":"Robust Acoustic Speech Feature Prediction From Noisy Mel-Frequency Cepstral Coefficients","display_name":"Robust Acoustic Speech Feature Prediction From Noisy Mel-Frequency Cepstral Coefficients","publication_year":2010,"publication_date":"2010-04-09","ids":{"openalex":"https://openalex.org/W2006051038","doi":"https://doi.org/10.1109/tasl.2010.2047811","mag":"2006051038"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2047811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2047811","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":[{"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":["School of Computing Sciences, University of East Anglia, UK","School of Computer Science, University of East Anglia, Norwich, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, UK","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"School of Computer Science, University of East Anglia, Norwich, UK#TAB#","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063817485","display_name":"Jonathan Darch","orcid":"https://orcid.org/0000-0001-6796-9041"},"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":"Jonathan Darch","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK","School of Computer Science, University of East Anglia, Norwich, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"School of Computer Science, University of East Anglia, Norwich, UK#TAB#","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":5.127,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9511565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"19","issue":"2","first_page":"338","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8180316090583801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7747071981430054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6759129166603088},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5954022407531738},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5917797088623047},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5833706855773926},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5527104139328003},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5523433089256287},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4892139434814453},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47921186685562134},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41408252716064453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40551427006721497},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3172917664051056},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2781606614589691},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16495144367218018},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.09055772423744202}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8180316090583801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7747071981430054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759129166603088},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5954022407531738},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5917797088623047},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5833706855773926},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5527104139328003},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5523433089256287},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4892139434814453},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47921186685562134},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41408252716064453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40551427006721497},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3172917664051056},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2781606614589691},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16495144367218018},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.09055772423744202},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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:10.1109/tasl.2010.2047811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2047811","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:22034","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/22034/","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":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W96504731","https://openalex.org/W105750483","https://openalex.org/W1800365115","https://openalex.org/W1968222399","https://openalex.org/W2018228148","https://openalex.org/W2052667477","https://openalex.org/W2060888333","https://openalex.org/W2064367225","https://openalex.org/W2091425152","https://openalex.org/W2117326161","https://openalex.org/W2137075158","https://openalex.org/W2146064606","https://openalex.org/W2146871184","https://openalex.org/W2149535104","https://openalex.org/W2155445312","https://openalex.org/W2157867825","https://openalex.org/W2164764235","https://openalex.org/W4298266977","https://openalex.org/W6603922934"],"related_works":["https://openalex.org/W2368661496","https://openalex.org/W1593591600","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"the":[3,84,122,137],"effect":[4,62],"of":[5,59,63,121,131],"applying":[6],"noise":[7,64,70,90,147],"compensation":[8,71,91,148],"to":[9,96,126],"acoustic":[10,28,124],"speech":[11,24,29,79,127,143,150],"feature":[12,30],"prediction":[13,97],"from":[14,43],"noisy":[15,153],"mel-frequency":[16],"cepstral":[17],"coefficient":[18],"(MFCC)":[19],"vectors":[20],"within":[21,83],"a":[22,48,50,103],"distributed":[23],"recognition":[25],"architecture.":[26],"An":[27],"(comprising":[31],"fundamental":[32],"frequency,":[33],"formant":[34],"frequencies,":[35],"speech/nonspeech":[36],"classification,":[37],"and":[38,67,115,145],"voicing":[39],"classification)":[40],"is":[41,65],"predicted":[42,123,138],"an":[44],"MFCC":[45],"vector":[46],"in":[47,77,152],"maximum":[49],"posteriori":[51],"(MAP)":[52],"framework":[53],"using":[54],"phoneme-specific":[55],"or":[56],"global":[57],"models":[58],"speech.":[60],"The":[61],"considered":[66],"three":[68],"different":[69],"methods,":[72],"that":[73,89,107,136,146],"have":[74],"been":[75],"successful":[76],"robust":[78],"recognition,":[80],"are":[81,140],"integrated":[82],"MAP":[85],"framework.":[86],"Experiments":[87],"show":[88,135],"can":[92],"be":[93],"applied":[94],"successfully":[95],"with":[98],"best":[99],"performance":[100],"given":[101],"by":[102],"model":[104],"adaptation":[105],"method":[106],"performs":[108],"only":[109],"slightly":[110],"worse":[111],"than":[112],"matched":[113],"training":[114],"testing.":[116],"Further":[117],"experiments":[118],"consider":[119],"application":[120],"features":[125,139],"reconstruction.":[128],"A":[129],"series":[130],"human":[132],"listening":[133],"tests":[134],"sufficient":[141],"for":[142],"reconstruction":[144],"improves":[149],"quality":[151],"conditions.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}