{"id":"https://openalex.org/W2125989302","doi":"https://doi.org/10.1109/icassp.2012.6288964","title":"ASR-driven top-down binary mask estimation using spectral priors","display_name":"ASR-driven top-down binary mask estimation using spectral priors","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2125989302","doi":"https://doi.org/10.1109/icassp.2012.6288964","mag":"2125989302"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288964","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/A5047770365","display_name":"William M. Hartmann","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Hartmann","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, USA","The Ohio State University,Department of Computer Science and Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, USA","The Ohio State University,Department of Computer Science and Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"4685","last_page":"4688"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9998000264167786,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.7601961493492126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6290772557258606},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6016721725463867},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.584904134273529},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5691829919815063},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.563449501991272},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5526512265205383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123277902603149},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4779077470302582},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46548452973365784},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4574391841888428},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.45435085892677307},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.445684552192688},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.44065964221954346},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43382734060287476},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.43199270963668823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16557687520980835},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11355122923851013},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11278575658798218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601961493492126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6290772557258606},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6016721725463867},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.584904134273529},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5691829919815063},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.563449501991272},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5526512265205383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123277902603149},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4779077470302582},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46548452973365784},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4574391841888428},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.45435085892677307},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.445684552192688},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44065964221954346},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43382734060287476},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.43199270963668823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16557687520980835},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11355122923851013},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11278575658798218},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288964","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:10.1.1.700.157","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.700.157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.betweenzeroandone.com/publications/hartmann_icassp2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W2029862345","https://openalex.org/W2036155843","https://openalex.org/W2074354966","https://openalex.org/W2103683411","https://openalex.org/W2106603795","https://openalex.org/W2128653836","https://openalex.org/W2131753991","https://openalex.org/W2143855671","https://openalex.org/W2145759598","https://openalex.org/W2561557072","https://openalex.org/W4233392025"],"related_works":["https://openalex.org/W4385545089","https://openalex.org/W3108403339","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W4401575680","https://openalex.org/W2025188156","https://openalex.org/W4287867034"],"abstract_inverted_index":{"Typical":[0],"mask":[1,22,26],"estimation":[2],"algorithms":[3],"use":[4],"low-level":[5],"features":[6],"to":[7,21,78],"estimate":[8],"the":[9,34,41,44,65,79,109],"interfering":[10],"noise":[11],"or":[12,43],"instantaneous":[13,45],"SNR.":[14,46],"We":[15,83],"propose":[16],"a":[17,30,53,60,96,124],"simple":[18],"top-down":[19],"approach":[20],"estimation.":[23],"The":[24],"estimated":[25],"is":[27],"based":[28],"on":[29,64],"specific":[31],"hypothesis":[32],"of":[33],"underlying":[35],"speech":[36,102,106,128],"without":[37],"using":[38],"information":[39,121],"about":[40],"interference":[42],"In":[47],"this":[48],"pilot":[49],"study,":[50],"we":[51],"observe":[52],"9%":[54],"reduction":[55],"in":[56,127],"word":[57],"error":[58],"over":[59],"baseline":[61],"recognition":[62,103,112],"system":[63],"Aurora4":[66],"corpus,":[67],"though":[68],"much":[69],"greater":[70],"gains":[71],"could":[72],"theoretically":[73],"be":[74,117],"achieved":[75],"through":[76],"improvements":[77],"model":[80],"selection":[81],"process.":[82],"also":[84],"present":[85],"SNR":[86],"improvement":[87],"results":[88],"showing":[89],"our":[90],"method":[91],"performs":[92],"as":[93,95],"well":[94],"standard":[97],"MMSE-based":[98],"method,":[99],"demonstrating":[100],"that":[101],"can":[104,122],"aid":[105],"enhancement.":[107,129],"Thus,":[108],"relationship":[110],"between":[111],"and":[113],"enhancement":[114],"need":[115],"not":[116],"one":[118],"way:":[119],"linguistic":[120],"play":[123],"significant":[125],"role":[126]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}