{"id":"https://openalex.org/W2127671620","doi":"https://doi.org/10.1109/icassp.2012.6288802","title":"LogMax observation model with MFCC-based spectral prior for reduction of highly nonstationary ambient noise","display_name":"LogMax observation model with MFCC-based spectral prior for reduction of highly nonstationary ambient noise","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2127671620","doi":"https://doi.org/10.1109/icassp.2012.6288802","mag":"2127671620"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs., NTT Corporation, 2-4, Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4029","last_page":"4032"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8806800842285156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.735601007938385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7219272255897522},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7093479633331299},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6979427337646484},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5484061241149902},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5346817970275879},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.526813268661499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5024700164794922},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46914616227149963},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4371541738510132},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.287727952003479},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1392841339111328}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8806800842285156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735601007938385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7219272255897522},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7093479633331299},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6979427337646484},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5484061241149902},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5346817970275879},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.526813268661499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5024700164794922},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46914616227149963},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4371541738510132},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.287727952003479},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1392841339111328},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1989954041","https://openalex.org/W2126597753","https://openalex.org/W2138889249","https://openalex.org/W2166458192","https://openalex.org/W2396455701","https://openalex.org/W2465697055","https://openalex.org/W6712212906","https://openalex.org/W6719417910"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2349769824","https://openalex.org/W2025614924","https://openalex.org/W2914532148","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W2160650576"],"abstract_inverted_index":{"This":[0],"paper":[1,112],"proposes":[2],"a":[3,11,64,102],"new":[4],"single/multi-channel":[5],"speech":[6,21,68,139,143],"enhancement":[7,69],"approach":[8,70,135],"based":[9,67],"on":[10],"LogMax":[12,34,90],"observation":[13,35],"model":[14,36,77,91],"integrated":[15],"with":[16,51,98],"Gaussian":[17],"mixture":[18],"models":[19],"of":[20,88,105,132],"and":[22,81,125,141],"noise":[23],"mel-frequency":[24],"cepstral":[25],"coefficients":[26],"(MFCC-GMM).":[27],"It":[28],"has":[29,37,59,92],"been":[30,61],"reported":[31],"that":[32,63],"the":[33,85,89,121,130,133],"high":[38],"potential":[39],"for":[40,45,78],"reducing":[41],"highly":[42],"nonstationary":[43],"noise,":[44],"example,":[46],"when":[47],"it":[48,58,97],"is":[49,101,113],"combined":[50],"factorial":[52],"hidden":[53],"Markov":[54],"models.":[55],"In":[56],"addition,":[57],"recently":[60],"shown":[62],"source":[65],"location":[66],"can":[71],"be":[72],"easily":[73],"incorporated":[74],"into":[75],"this":[76,106,111,117],"more":[79],"efficient":[80],"reliable":[82],"estimation.":[83],"However,":[84],"unique":[86],"structure":[87],"prevented":[93],"us":[94],"from":[95],"using":[96,120],"MFCC-GMMs,":[99],"which":[100],"fundamental":[103],"limitation":[104],"approach.":[107],"Our":[108],"proposal":[109],"in":[110],"aimed":[114],"at":[115],"overcoming":[116],"limitation.":[118],"Experiments":[119],"PASCAL":[122],"CHiME":[123],"separation":[124],"recognition":[126,144],"challenge":[127],"task":[128],"show":[129],"superiority":[131],"proposed":[134],"as":[136],"regards":[137],"both":[138],"quality":[140],"automatic":[142],"performance.":[145]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}