{"id":"https://openalex.org/W2145759598","doi":"https://doi.org/10.1109/icassp.2011.5947430","title":"Investigations into the incorporation of the Ideal Binary Mask in ASR","display_name":"Investigations into the incorporation of the Ideal Binary Mask in ASR","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2145759598","doi":"https://doi.org/10.1109/icassp.2011.5947430","mag":"2145759598"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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 Uinversity, 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 Uinversity, 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 Uinversity, 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 Uinversity, 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":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4804","last_page":"4807"},"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":0.9995999932289124,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894589900970459},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.7533214092254639},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6919876337051392},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.6417813301086426},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5966470837593079},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4167039394378662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3943585753440857},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34413039684295654},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.12012538313865662},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11215183138847351},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1048731803894043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894589900970459},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.7533214092254639},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6919876337051392},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.6417813301086426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5966470837593079},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4167039394378662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3943585753440857},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34413039684295654},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.12012538313865662},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11215183138847351},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1048731803894043},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.699.8479","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.699.8479","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_icassp2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1979099822","https://openalex.org/W2074354966","https://openalex.org/W2126622418","https://openalex.org/W2143855671","https://openalex.org/W2145475542","https://openalex.org/W2154803122","https://openalex.org/W4245919820"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2072507639","https://openalex.org/W2004554462","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"While":[0],"much":[1],"work":[2,126],"has":[3],"been":[4],"dedicated":[5],"to":[6,10,71,137],"exploring":[7],"how":[8],"best":[9],"incorporate":[11],"the":[12,28,42,46,49,53,56,72,75,79,92,118,121,130],"Ideal":[13],"Binary":[14],"Mask":[15],"(IBM)":[16],"in":[17,105,112,117,123],"automatic":[18],"speech":[19,33,83,135],"recognition":[20],"(ASR)":[21],"for":[22,95],"noisy":[23],"signals,":[24],"we":[25],"demonstrate":[26],"that":[27],"simple":[29],"use":[30,80,132],"of":[31,44,48,55,65,74,81,88,120,133],"masked":[32,82,134],"can":[34,108],"outperform":[35],"standard":[36],"spectral":[37,96],"reconstruction":[38,97],"methods.":[39],"We":[40],"explore":[41],"effects":[43],"both":[45],"accuracy":[47,73],"mask":[50,106],"estimation":[51,107],"and":[52],"strength":[54],"language":[57,146],"model":[58],"on":[59,141],"our":[60],"results.":[61],"The":[62],"relative":[63],"performance":[64,94,114,140],"these":[66],"techniques":[67,98],"is":[68],"directly":[69],"tied":[70],"estimated":[76],"mask.":[77],"Although":[78],"fails":[84],"when":[85],"significant":[86],"numbers":[87],"errors":[89],"are":[90],"present,":[91],"maximum":[93],"also":[99],"drops":[100],"significantly.":[101],"This":[102],"implies":[103],"improvements":[104,116],"provide":[109],"greater":[110],"gains":[111],"ASR":[113],"than":[115],"incorporation":[119],"IBM":[122],"ASR.":[124],"Previous":[125],"may":[127],"have":[128],"ignored":[129],"direct":[131],"due":[136],"its":[138],"poor":[139],"tasks":[142],"without":[143],"a":[144],"strong":[145],"model.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
