{"id":"https://openalex.org/W2066850331","doi":"https://doi.org/10.1109/icassp.2013.6638982","title":"Coupling binary masking and robust ASR","display_name":"Coupling binary masking and robust ASR","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2066850331","doi":"https://doi.org/10.1109/icassp.2013.6638982","mag":"2066850331"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":"Arun Narayanan","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","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 University, Columbus, OH, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center for Cognitive Science, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.6078,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84087633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6817","last_page":"6821"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7641428709030151},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.7187072038650513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7128916382789612},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6385060548782349},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6292405724525452},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5912367701530457},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5586622953414917},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5491840243339539},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5217926502227783},{"id":"https://openalex.org/keywords/binary-code","display_name":"Binary code","score":0.4707779586315155},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4620342552661896},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4252474009990692},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3578184247016907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3103915750980377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18288329243659973},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10396784543991089},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0686633288860321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641428709030151},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7187072038650513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7128916382789612},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6385060548782349},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6292405724525452},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5912367701530457},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5586622953414917},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5491840243339539},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5217926502227783},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.4707779586315155},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4620342552661896},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4252474009990692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3578184247016907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3103915750980377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18288329243659973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10396784543991089},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0686633288860321},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.2192","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.2192","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/Narayanan-Wang1.icassp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"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":36,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W121116918","https://openalex.org/W160800111","https://openalex.org/W1495679096","https://openalex.org/W1635512741","https://openalex.org/W1963970749","https://openalex.org/W1986225048","https://openalex.org/W1989364685","https://openalex.org/W2002342963","https://openalex.org/W2029177977","https://openalex.org/W2029862345","https://openalex.org/W2045036776","https://openalex.org/W2047919706","https://openalex.org/W2062518906","https://openalex.org/W2074354966","https://openalex.org/W2086139506","https://openalex.org/W2087126002","https://openalex.org/W2100046100","https://openalex.org/W2106603795","https://openalex.org/W2120933697","https://openalex.org/W2126622418","https://openalex.org/W2131753991","https://openalex.org/W2137075158","https://openalex.org/W2146083413","https://openalex.org/W2155445312","https://openalex.org/W2163648514","https://openalex.org/W2163680580","https://openalex.org/W2394675549","https://openalex.org/W2402267837","https://openalex.org/W2406650081","https://openalex.org/W2561557072","https://openalex.org/W2619993508","https://openalex.org/W3021396111","https://openalex.org/W4233392025","https://openalex.org/W4245919820","https://openalex.org/W4256399001"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W2100203012","https://openalex.org/W2044344400","https://openalex.org/W2353790262","https://openalex.org/W4253186488","https://openalex.org/W1996938127","https://openalex.org/W2043380045","https://openalex.org/W2732495365","https://openalex.org/W2022349254","https://openalex.org/W2154434735"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,16,38,62,99,136],"novel":[3],"framework":[4,134],"for":[5,98],"performing":[6],"speech":[7,12,31,77],"separation":[8,66],"and":[9,33],"robust":[10,129],"automatic":[11],"recognition":[13],"(ASR)":[14],"in":[15,37,61,141,154],"unified":[17],"fashion.":[18],"Separation":[19],"is":[20,47,95,112],"performed":[21,48],"by":[22,68,87],"estimating":[23],"the":[24,43,106,127,132,146,155,158],"ideal":[25],"binary":[26,54],"mask":[27],"(IBM),":[28],"which":[29,73,94],"identifies":[30],"dominant":[32,35],"noise":[34],"units":[36],"time-frequency":[39],"(T-F)":[40],"representation":[41],"of":[42,93,105,139,157],"noisy":[44,147],"signal.":[45],"ASR":[46,110,130],"on":[49],"extracted":[50],"cepstral":[51],"features":[52],"after":[53],"masking.":[55],"Previous":[56],"systems":[57],"perform":[58],"these":[59,81,116],"steps":[60],"sequential":[63],"fashion":[64],"-":[65],"followed":[67],"recognition.":[69],"The":[70,108],"proposed":[71,133],"framework,":[72],"we":[74],"call":[75],"bidirectional":[76],"decoding":[78],"(BSD),":[79],"unifies":[80],"two":[82],"stages.":[83],"It":[84,149],"does":[85],"this":[86],"using":[88],"multiple":[89],"IBM":[90,117],"estimators":[91,118],"each":[92],"designed":[96],"specifically":[97],"back-end":[100],"acoustic":[101],"phonetic":[102],"unit":[103],"(BPU)":[104],"recognizer.":[107],"standard":[109],"decoder":[111],"modified":[113],"to":[114,119],"use":[115],"obtain":[120],"BPU-specific":[121],"cepstra":[122],"during":[123],"likelihood":[124],"calculation.":[125],"On":[126],"Aurora-4":[128],"task,":[131],"obtains":[135,151],"relative":[137],"improvement":[138],"17%":[140],"word":[142],"error":[143],"rate":[144],"over":[145],"baseline.":[148],"also":[150],"significant":[152],"improvements":[153],"quality":[156],"estimated":[159],"IBM.":[160]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}