{"id":"https://openalex.org/W1998460627","doi":"https://doi.org/10.1121/1.415961","title":"Cepstral representation of speech motivated by time\u2013frequency masking: An application to speech recognition","display_name":"Cepstral representation of speech motivated by time\u2013frequency masking: An application to speech recognition","publication_year":1996,"publication_date":"1996-07-01","ids":{"openalex":"https://openalex.org/W1998460627","doi":"https://doi.org/10.1121/1.415961","mag":"1998460627","pmid":"https://pubmed.ncbi.nlm.nih.gov/8675851"},"language":"en","primary_location":{"id":"doi:10.1121/1.415961","doi":"https://doi.org/10.1121/1.415961","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.415961","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"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/A5111611754","display_name":"Kiyoaki Aikawa","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiyoaki Aikawa","raw_affiliation_strings":["ATR Human Information Processing Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Human Information Processing Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112243886","display_name":"Harald Singer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Harald Singer","raw_affiliation_strings":["ATR Interpreting Telecommunications Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Interpreting Telecommunications Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072749858","display_name":"Hideki Kawahara","orcid":"https://orcid.org/0000-0001-9360-5700","observed_orcids":["https://orcid.org/0000-0001-9360-5700"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hideki Kawahara","raw_affiliation_strings":["ATR Human Information Processing Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Human Information Processing Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639224","display_name":"Yoh\u2019ichi Tohkura","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoh\u2019ichi Tohkura","raw_affiliation_strings":["ATR Human Information Processing Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Human Information Processing Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4759,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.71283375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"100","issue":"1","first_page":"603","last_page":"614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9854000210762024,"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":0.9854000210762024,"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":0.013500000350177288,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/time-frequency-masking","display_name":"time-frequency masking","score":0.7860000133514404},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6330000162124634},{"id":"https://openalex.org/keywords/phoneme-classification","display_name":"phoneme classification","score":0.8899999856948853},{"id":"https://openalex.org/keywords/phrase-recognition","display_name":"phrase recognition","score":0.972000002861023},{"id":"https://openalex.org/keywords/speaker-independent-speech-recognition","display_name":"speaker-independent recognition","score":0.8389999866485596},{"id":"https://openalex.org/keywords/formant-transitions","display_name":"formant transitions","score":0.7459999918937683},{"id":"https://openalex.org/keywords/spectral-smoothing","display_name":"spectral smoothing","score":0.8539999723434448},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"linear predictive coding","score":0.6230000257492065},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.7440000176429749},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7409999966621399}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.8473948240280151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7698007822036743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6267164945602417},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5256360769271851},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4808943271636963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47476887702941895},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.4608139395713806},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4547237455844879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43205520510673523},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41592830419540405},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2483699917793274},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010470","descriptor_name":"Perceptual Masking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010700","descriptor_name":"Phonetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1121/1.415961","doi":"https://doi.org/10.1121/1.415961","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.415961","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},{"id":"pmid:8675851","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/8675851","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2134445571","https://openalex.org/W1974806042","https://openalex.org/W2103387126","https://openalex.org/W1992474372","https://openalex.org/W2127043613","https://openalex.org/W2167033870","https://openalex.org/W7030544115","https://openalex.org/W2089366861","https://openalex.org/W7096710803","https://openalex.org/W2124770629"],"abstract_inverted_index":{"A":[0],"new":[1,43],"spectral":[2,12,44,65,79,134],"representation":[3,13,45],"incorporating":[4],"time-frequency":[5],"forward":[6],"masking":[7],"is":[8,14,115],"proposed.":[9],"This":[10,42],"masked":[11],"efficiently":[15,91],"represented":[16],"by":[17,171,225],"a":[18,47,100,104,111,118,123,139,146,149,153,207,213],"quefrency":[19],"domain":[20],"parameter":[21,156,188],"called":[22],"dynamic-cepstrum":[23],"(DyC).":[24],"Automatic":[25],"speech":[26,87,193,203],"recognition":[27,170,204],"experiments":[28],"have":[29],"demonstrated":[30],"that":[31],"DyC":[32,89,114,151,196],"powerfully":[33],"improves":[34],"performance":[35,205],"in":[36,191],"phoneme":[37,59,166],"classification":[38,167,220],"and":[39,96,148,168,212],"phrase":[40,169],"recognition.":[41,88,194],"simulates":[46],"perceived":[48],"spectrum.":[49],"It":[50],"enhances":[51],"formant":[52],"transition,":[53],"which":[54],"provides":[55],"relevant":[56],"cues":[57],"for":[58,85,164,218],"perception,":[60],"while":[61],"suppressing":[62],"temporally":[63],"stationary":[64],"properties,":[66],"such":[67],"as":[68,110],"the":[69,76,94,107,130,142,186,210,219],"effect":[70],"of":[71,99,106,129,141,209,222],"microphone":[72],"frequency":[73],"characteristics":[74,137],"or":[75],"speaker-dependent":[77,179],"time-invariant":[78],"feature.":[80],"These":[81],"features":[82],"are":[83,138],"advantageous":[84],"speaker-independent":[86,192],"can":[90],"represent":[92],"both":[93,165],"instantaneous":[95],"transitional":[97],"aspects":[98],"running":[101],"spectrum":[102],"with":[103,178,197,215],"vector":[105,128],"same":[108],"size":[109],"conventional":[112,154],"cepstrum.":[113],"calculated":[116],"from":[117],"cepstrum":[119,155,187,211],"time":[120,143],"sequence":[121],"using":[122,172],"matrix":[124,131],"lifter.":[125],"Each":[126],"column":[127],"lifter":[132],"performs":[133],"smoothing.":[135],"Smoothing":[136],"function":[140],"interval":[144],"between":[145],"masker":[147],"signal.":[150],"outperformed":[152],"obtained":[157],"through":[158],"linear":[159],"predictive":[160],"coding":[161],"(LPC)":[162],"analysis":[163],"hidden":[173],"Markov":[174],"models":[175],"(HMMs).":[176],"Compared":[177],"recognition,":[180],"an":[181],"even":[182],"greater":[183],"improvement":[184],"over":[185],"was":[189],"found":[190],"Furthermore,":[195],"only":[198],"16":[199],"coefficients":[200,217],"exhibited":[201],"higher":[202],"than":[206],"combination":[208],"delta-cepstrum":[214],"32":[216],"experiment":[221],"phonemes":[223],"contaminated":[224],"noises.":[226]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}