{"id":"https://openalex.org/W2076979746","doi":"https://doi.org/10.1109/icassp.2002.5743691","title":"Cepstrum-domain model combination based on decomposition of speech and noise for noisy speech recognition","display_name":"Cepstrum-domain model combination based on decomposition of speech and noise for noisy speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2076979746","doi":"https://doi.org/10.1109/icassp.2002.5743691","mag":"2076979746"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743691","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hong Kook Kim","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA","AT&T Laboratories \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Laboratories \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077077136","display_name":"Richard C. Rose","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard C. Rose","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA","AT&T Laboratories \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Laboratories \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085604883"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":0.9893,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.69118905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"209"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9987999796867371,"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/cepstrum","display_name":"Cepstrum","score":0.8336864113807678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7826962471008301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7306398153305054},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7180911302566528},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5945988297462463},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5355377793312073},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5101180672645569},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5029451251029968},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4855732321739197},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4409271776676178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43649396300315857},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4254779517650604},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.42511898279190063},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34339937567710876},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2817874252796173}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.8336864113807678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7826962471008301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306398153305054},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7180911302566528},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5945988297462463},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5355377793312073},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5101180672645569},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5029451251029968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4855732321739197},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4409271776676178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43649396300315857},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4254779517650604},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.42511898279190063},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34339937567710876},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2817874252796173},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743691","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.596.9465","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.596.9465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.mcgill.ca/~rrose1/papers/kim_rose_aslp2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W269674882","https://openalex.org/W1614028504","https://openalex.org/W1920183217","https://openalex.org/W2045036776","https://openalex.org/W2059736174","https://openalex.org/W2121894251","https://openalex.org/W2150660184","https://openalex.org/W2151484683","https://openalex.org/W2158336491","https://openalex.org/W2160806989","https://openalex.org/W2161151281","https://openalex.org/W2168362601","https://openalex.org/W6682194319"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2066371342"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,76,78,89,134],"cepstrum-domain":[3],"model":[4,52,83,116,127],"combination":[5,53,117],"method":[6,19],"for":[7,49,88],"automatic":[8],"speech":[9,23,28,72,80,102],"recognition":[10,138],"in":[11,33,143],"noisy":[12,135],"environments.":[13],"The":[14,111,129],"distinguishing":[15],"aspect":[16],"of":[17,62,99,106,113],"the":[18,34,42,60,63,94,100,114],"is":[20,24,47,56,85,119],"that":[21],"noise-corrupted":[22,90],"decomposed":[25],"into":[26],"clean":[27,79,101],"and":[29,96,104,161],"noise":[30,109],"components":[31],"directly":[32],"cepstrum":[35],"domain":[36,45,91],"without":[37],"having":[38],"to":[39,41,124,133],"transform":[40],"linear":[43],"spectrum":[44],"as":[46],"necessary":[48],"many":[50],"existing":[51],"approaches.":[54],"This":[55],"accomplished":[57],"by":[58,92],"exploiting":[59],"properties":[61],"minimum":[64],"mean":[65],"squared":[66],"error-log":[67],"spectral":[68],"amplitude":[69],"(MMSE-LSA)":[70],"based":[71],"enhancement":[73],"algorithm.":[74],"As":[75],"result,":[77],"hidden":[81],"Markov":[82],"(HMM)":[84],"easily":[86],"compensated":[87],"adding":[93],"means":[95],"covariance":[97],"matrices":[98],"HMM":[103],"those":[105],"an":[107],"estimated":[108],"model.":[110],"complexity":[112],"proposed":[115],"procedure":[118,130],"significantly":[120],"reduced":[121],"with":[122,153],"respect":[123],"conventional":[125],"parallel":[126],"combination.":[128],"was":[131,147,151],"applied":[132],"connected":[136],"digit":[137],"task.":[139],"A":[140],"40%":[141],"reduction":[142],"word":[144],"error":[145],"rate":[146],"achieved":[148],"when":[149],"it":[150],"combined":[152],"acoustic":[154],"feature":[155],"compensation":[156],"techniques":[157],"under":[158],"mismatched":[159],"environmental":[160],"channel":[162],"conditions.":[163]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}