{"id":"https://openalex.org/W2163674618","doi":"https://doi.org/10.1109/icassp.2012.6287863","title":"Introduction of speech log-spectral priors into dereverberation based on Itakura-Saito distance minimization","display_name":"Introduction of speech log-spectral priors into dereverberation based on Itakura-Saito distance minimization","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2163674618","doi":"https://doi.org/10.1109/icassp.2012.6287863","mag":"2163674618"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287863","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/A5086311889","display_name":"Yasuaki Iwata","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"]},{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuaki Iwata","raw_affiliation_strings":["Graduate School of Information Science, University of Nagoya, Aichi, Japan","NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, University of Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"248"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9972000122070312,"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/prior-probability","display_name":"Prior probability","score":0.7905309200286865},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6735826134681702},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6067938208580017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5977309942245483},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49999141693115234},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.4859832227230072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47808384895324707},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4508599042892456},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.41208741068840027},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39887261390686035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35890674591064453},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.3329349160194397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.297914981842041},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15245503187179565},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1286628544330597},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10983026027679443}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7905309200286865},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6735826134681702},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6067938208580017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5977309942245483},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49999141693115234},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.4859832227230072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47808384895324707},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4508599042892456},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41208741068840027},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39887261390686035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35890674591064453},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3329349160194397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.297914981842041},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15245503187179565},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1286628544330597},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10983026027679443},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6287863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287863","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.851.7841","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.851.7841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202012/pdfs/0000245.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"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":5,"referenced_works":["https://openalex.org/W1808196926","https://openalex.org/W2039844283","https://openalex.org/W2164502538","https://openalex.org/W2165534711","https://openalex.org/W4296927107"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W2042717753","https://openalex.org/W3142333283","https://openalex.org/W2580650124","https://openalex.org/W1839961359","https://openalex.org/W2075146114","https://openalex.org/W2100805585","https://openalex.org/W2360887461"],"abstract_inverted_index":{"It":[0],"has":[1],"recently":[2],"been":[3],"shown":[4],"that":[5,44],"a":[6,32,86,96,106,119,134],"multi-channel":[7],"linear":[8],"prediction":[9],"can":[10,23],"effectively":[11],"achieve":[12],"blind":[13],"speech":[14,45,74,102,109],"dereverberation":[15,53],"based":[16,57,83],"on":[17,58,84],"maximum-likelihood":[18],"(ML)":[19],"estimation.":[20,89],"This":[21],"approach":[22,42],"estimate":[24],"and":[25,80,105],"cancel":[26],"unknown":[27],"reverberation":[28],"processes":[29],"from":[30],"only":[31],"few":[33],"seconds":[34],"of":[35,92,101,108,143],"observation.":[36],"However,":[37],"one":[38],"problem":[39],"with":[40,128],"this":[41,70,78],"is":[43],"distortion":[46],"may":[47],"increase":[48],"if":[49],"we":[50,72,116],"iterate":[51],"the":[52,66,114,129,141,144],"more":[54],"than":[55],"once":[56],"Itakura-Saito":[59],"(IS)":[60],"distance":[61,131],"minimization":[62,132],"to":[63,123],"further":[64],"reduce":[65],"reverberation.":[67],"To":[68],"overcome":[69],"problem,":[71],"introduce":[73],"log-spectral":[75,126],"priors":[76,93,127],"into":[77],"approach,":[79],"reformulate":[81],"it":[82],"maximum":[85],"posteriori":[87],"(MAP)":[88],"Two":[90],"types":[91],"are":[94],"introduced,":[95],"Gaussian":[97],"mixture":[98],"model":[99],"(GMM)":[100],"log":[103],"spectra,":[104],"GMM":[107],"mel-frequency":[110],"cepstral":[111],"coefficients.":[112],"In":[113],"formulation,":[115],"also":[117],"propose":[118],"new":[120],"versatile":[121],"technique":[122],"integrate":[124],"such":[125],"IS":[130],"in":[133],"computationally":[135],"efficient":[136],"manner.":[137],"Preliminary":[138],"experiments":[139],"show":[140],"effectiveness":[142],"proposed":[145],"approach.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}