{"id":"https://openalex.org/W1224261078","doi":"https://doi.org/10.21437/icslp.2000-768","title":"The effects of room acoustics on MFCC speech parameter","display_name":"The effects of room acoustics on MFCC speech parameter","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W1224261078","doi":"https://doi.org/10.21437/icslp.2000-768","mag":"1224261078"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-768","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108053345","display_name":"Yue Pan","orcid":"https://orcid.org/0000-0003-4572-8882"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Pan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000249424","display_name":"Alex Waibel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"vol. 4, 129","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9902999997138977,"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/reverberation","display_name":"Reverberation","score":0.7744218111038208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7463831305503845},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6496226787567139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6143133044242859},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5755852460861206},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5703502893447876},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.568813681602478},{"id":"https://openalex.org/keywords/room-acoustics","display_name":"Room acoustics","score":0.5522253513336182},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48082196712493896},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4779669940471649},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45161983370780945},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.42096078395843506},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.41271576285362244},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.30303001403808594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28662729263305664},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.16081008315086365},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1165350079536438},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10861477255821228},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.09511673450469971},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.078209787607193}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7744218111038208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7463831305503845},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6496226787567139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6143133044242859},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5755852460861206},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5703502893447876},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.568813681602478},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.5522253513336182},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48082196712493896},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4779669940471649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45161983370780945},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.42096078395843506},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.41271576285362244},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30303001403808594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28662729263305664},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.16081008315086365},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1165350079536438},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10861477255821228},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.09511673450469971},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.078209787607193},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2000-768","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.37.106","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.37.106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.is.cs.cmu.edu/papers/speech/ICSLP2000/ICSLP2000-yue.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1552594198","https://openalex.org/W2008957275","https://openalex.org/W2121039197","https://openalex.org/W2125278480","https://openalex.org/W2154073246","https://openalex.org/W2167193734"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2432604435","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W2089229568"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,45,57],"recognition":[2],"systems":[3],"attain":[4],"high":[5],"performance":[6],"for":[7,34],"close-talking":[8],"applications,":[9],"but":[10],"they":[11],"deteriorate":[12],"significantly":[13],"in":[14,120],"distant-talking":[15],"environment.":[16],"The":[17,59,79],"reason":[18],"is":[19,132],"the":[20,39,75,83,86,89,92,95,98,105,116,121,136,139],"mismatch":[21],"between":[22],"training":[23,110],"and":[24,54,67,101],"testing":[25],"conditions.":[26],"We":[27],"have":[28],"carried":[29],"out":[30],"a":[31,35],"research":[32],"work":[33],"better":[36],"understanding":[37],"of":[38,41,51,61,85,107,138],"effects":[40],"room":[42,68],"acoustics":[43],"on":[44,74,82,141],"feature":[46,142],"by":[47],"comparing":[48],"simultaneous":[49],"recordings":[50],"close":[52],"talking":[53,56],"distant":[55],"utterances.":[58],"characteristics":[60],"two":[62],"degrading":[63],"sources,":[64],"background":[65],"noise":[66,80],"reverberation":[69,90],"are":[70,77],"discussed.":[71],"Their":[72],"impacts":[73],"spectrum":[76,87,123],"different.":[78],"affects":[81],"valley":[84],"while":[88],"causes":[91],"distortion":[93],"at":[94,97],"peaks":[96],"pitch":[99],"frequency":[100],"its":[102],"multiples.":[103],"In":[104],"situation":[106],"very":[108],"few":[109],"data,":[111],"we":[112],"attempt":[113],"to":[114,134],"choose":[115],"efficient":[117],"compensation":[118],"approaches":[119],"spectrum,":[122],"subband":[124],"or":[125],"cepstrum":[126],"domain.":[127],"Vector":[128],"Quantization":[129],"based":[130],"model":[131],"used":[133],"study":[135],"influence":[137],"variation":[140],"vector":[143],"distribution.":[144],"...":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}