{"id":"https://openalex.org/W2147442641","doi":"https://doi.org/10.1109/icassp.2006.1660103","title":"Robust Speaker Recognition Using Binary Time-Frequency Masks","display_name":"Robust Speaker Recognition Using Binary Time-Frequency Masks","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2147442641","doi":"https://doi.org/10.1109/icassp.2006.1660103","mag":"2147442641"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5079984408","display_name":"Yang Shao","orcid":"https://orcid.org/0000-0002-4870-7406"},"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":true,"raw_author_name":"Yang Shao","raw_affiliation_strings":["Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","Dept. of Computer Science and Engineering, Ohio State University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"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":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","Dept. of Computer Science and Engineering, Ohio State University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079984408"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.8621,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.90969525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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/binary-number","display_name":"Binary number","score":0.7909795641899109},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7348431348800659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6823914647102356},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6730951070785522},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6219360828399658},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5585952997207642},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5336416959762573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5303179621696472},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5006396770477295},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.4535478353500366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4511781930923462},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44719457626342773},{"id":"https://openalex.org/keywords/binary-data","display_name":"Binary data","score":0.4183483123779297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16355684399604797},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08285492658615112}],"concepts":[{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.7909795641899109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348431348800659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6823914647102356},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6730951070785522},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6219360828399658},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5585952997207642},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5336416959762573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5303179621696472},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5006396770477295},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.4535478353500366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4511781930923462},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44719457626342773},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.4183483123779297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16355684399604797},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08285492658615112},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1660103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.126.9421","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.126.9421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Shao-Wang.icassp06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1639266067","https://openalex.org/W1875231349","https://openalex.org/W1951870577","https://openalex.org/W1973746598","https://openalex.org/W2013020033","https://openalex.org/W2034040413","https://openalex.org/W2069883713","https://openalex.org/W2074354966","https://openalex.org/W2128202590","https://openalex.org/W2149425615","https://openalex.org/W2157906748","https://openalex.org/W2407400339","https://openalex.org/W3216401400","https://openalex.org/W4285719527","https://openalex.org/W6636614438","https://openalex.org/W6639350448","https://openalex.org/W6679445831","https://openalex.org/W6713851302"],"related_works":["https://openalex.org/W4388311650","https://openalex.org/W1974056099","https://openalex.org/W4245343541","https://openalex.org/W2386077341","https://openalex.org/W563589758","https://openalex.org/W5922282","https://openalex.org/W3081694532","https://openalex.org/W2954004777","https://openalex.org/W2949638731","https://openalex.org/W2951102138"],"abstract_inverted_index":{"Conventional":[0],"speaker":[1,19,55,116],"recognition":[2],"systems":[3],"perform":[4,54],"poorly":[5],"under":[6,64],"noisy":[7],"conditions.":[8],"In":[9],"this":[10],"paper,":[11],"we":[12,93],"evaluate":[13],"binary":[14,23,31,75,91,108],"time-frequency":[15,47],"masks":[16],"for":[17,114],"robust":[18,115],"recognition.":[20,117],"An":[21],"ideal":[22,74,90],"mask":[24,76],"is":[25,39],"a":[26,30,60,83,111],"priori":[27],"defined":[28],"as":[29],"matrix":[32],"where":[33],"1":[34],"indicates":[35,51],"that":[36,72,87,104],"the":[37,42,45,73,89,105],"target":[38],"stronger":[40],"than":[41],"interference":[43],"within":[44],"corresponding":[46],"unit":[48],"and":[49,57,66,70],"0":[50],"otherwise.":[52],"We":[53],"identification":[56],"verification":[58],"using":[59],"missing":[61],"data":[62],"recognizer":[63],"cochannel":[65],"other":[67],"noise":[68],"conditions,":[69],"show":[71],"provides":[77],"large":[78],"performance":[79],"gains.":[80],"By":[81],"employing":[82],"speech":[84],"segregation":[85],"system":[86],"estimates":[88],"mask,":[92],"achieve":[94],"significant":[95],"improvements":[96],"over":[97],"alternative":[98],"approaches.":[99],"Our":[100],"study,":[101],"thus,":[102],"demonstrates":[103],"use":[106],"of":[107],"masking":[109],"represents":[110],"promising":[112],"direction":[113]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}