{"id":"https://openalex.org/W1891548836","doi":"https://doi.org/10.21437/eurospeech.2003-24","title":"Integrated pitch and MFCC extraction for speech reconstruction and speech recognition applications","display_name":"Integrated pitch and MFCC extraction for speech reconstruction and speech recognition applications","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1891548836","doi":"https://doi.org/10.21437/eurospeech.2003-24","mag":"1891548836"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-24","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-24","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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":[{"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":"Xu Shao","raw_affiliation_strings":["#N#University of East Anglia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of East Anglia","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","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":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103796951","display_name":"Stephen Cox","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen J. Cox","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1865,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78949849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1725","last_page":"1728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7992340326309204},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7614572644233704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748719334602356},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7282109260559082},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5893824100494385},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.4732052683830261},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4606073200702667},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43895334005355835},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4333258867263794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38782867789268494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37225449085235596},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06970945000648499}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7992340326309204},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7614572644233704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748719334602356},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7282109260559082},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5893824100494385},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.4732052683830261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4606073200702667},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43895334005355835},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4333258867263794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38782867789268494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37225449085235596},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06970945000648499}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.2003-24","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-24","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.4470","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.4470","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_03.pdf","raw_type":"text"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:23132","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/23132/","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":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W293337345","https://openalex.org/W1984357105","https://openalex.org/W1989164285","https://openalex.org/W2069501481","https://openalex.org/W2115896199","https://openalex.org/W2469991276"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W3146151004","https://openalex.org/W2141992701","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2051008990","https://openalex.org/W2371980090"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,26],"integrated":[4],"speech":[5,9,12,120],"front-end":[6],"for":[7],"both":[8,38,89],"recognition":[10,97],"and":[11,42,65,76,92,113,127,138],"reconstruction":[13],"applications.":[14],"Speech":[15,96],"is":[16,33],"first":[17],"decomposed":[18],"into":[19],"a":[20,48],"set":[21],"of":[22,31,71],"frequency":[23],"bands":[24],"by":[25],"auditory":[27,51],"model.":[28],"The":[29],"output":[30],"this":[32,57],"then":[34],"used":[35,47],"to":[36,62,84,109,132],"extract":[37],"robust":[39,87],"pitch":[40,73,79,94,128],"estimates":[41],"MFCC":[43],"vectors.":[44],"Initial":[45],"tests":[46,116],"128":[49],"channel":[50],"model,":[52],"but":[53],"results":[54,98],"show":[55,99],"that":[56,100,119,133],"can":[58],"be":[59,85],"reduced":[60],"significantly":[61],"between":[63],"23":[64],"32":[66],"channels.":[67],"A":[68],"detailed":[69],"analysis":[70],"the":[72,77,82,101,123],"classification":[74],"accuracy":[75],"RMS":[78],"error":[80],"shows":[81],"system":[83],"more":[86],"than":[88],"comb":[90],"function":[91],"LPC-based":[93],"extraction.":[95],"auditory-based":[102,124],"cepstral":[103,125],"coefficients":[104,126],"give":[105],"very":[106],"similar":[107,130],"performance":[108],"conventional":[110,136],"MFCCs.":[111],"Spectrograms":[112],"informal":[114],"listening":[115],"also":[117],"reveal":[118],"reconstructed":[121,134],"from":[122,135],"has":[129],"quality":[131],"MFCCs":[137],"pitch.":[139],"1.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}