{"id":"https://openalex.org/W2399251227","doi":"https://doi.org/10.21437/interspeech.2012-381","title":"On the role of binary mask pattern in automatic speech recognition","display_name":"On the role of binary mask pattern in automatic speech recognition","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2399251227","doi":"https://doi.org/10.21437/interspeech.2012-381","mag":"2399251227"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-381","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"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":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","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":0.7345,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76304963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1239","last_page":"1242"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987000226974487,"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/binary-number","display_name":"Binary number","score":0.7790021300315857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7612737417221069},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6503288745880127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6495692729949951},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5986048579216003},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5935441255569458},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5532999634742737},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4914337396621704},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.475197434425354},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4743448793888092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4220430552959442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22189146280288696},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14887282252311707},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0987173318862915},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06489256024360657}],"concepts":[{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.7790021300315857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7612737417221069},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6503288745880127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6495692729949951},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5986048579216003},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5935441255569458},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5532999634742737},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4914337396621704},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.475197434425354},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4743448793888092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4220430552959442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22189146280288696},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14887282252311707},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0987173318862915},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06489256024360657},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-381","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1575829986","https://openalex.org/W2029177977","https://openalex.org/W2068011078","https://openalex.org/W2075076415","https://openalex.org/W2087126002","https://openalex.org/W2137094732","https://openalex.org/W2141998673","https://openalex.org/W2143855671","https://openalex.org/W2152131029","https://openalex.org/W2539207221"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W2368038768","https://openalex.org/W111365173","https://openalex.org/W2386453889"],"abstract_inverted_index":{"Processing":[0],"noisy":[1,198],"signals":[2,175],"using":[3],"the":[4,23,28,53,68,75,80,103,116,119,126,152,164,170,187],"ideal":[5],"binary":[6,95],"mask":[7,31,43],"has":[8],"been":[9],"shown":[10],"to":[11,91,125,140,190],"improve":[12,99,191],"automatic":[13],"speech":[14,93,145],"recognition":[15,127,196],"(ASR)":[16],"performance.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"present":[22],"first":[24],"study":[25],"that":[26,180],"investigates":[27],"role":[29],"of":[30,60,84,173,197],"patterns":[32],"in":[33,135],"ASR":[34,100,136],"under":[35],"varying":[36],"signalto-noise":[37],"ratios":[38],"(SNR),":[39],"noise":[40],"conditions":[41],"and":[42,118],"definitions.":[44],"Binary":[45],"masks":[46],"are":[47,137],"typically":[48],"computed":[49],"either":[50,192],"by":[51,73],"comparing":[52,74],"local":[54,69,76],"SNR":[55,105,121,171,182],"within":[56],"a":[57,61,65],"time-frequency":[58],"unit":[59],"mixture":[62,104,120],"signal":[63],"with":[64,79],"threshold":[66,166],"termed":[67],"criterion":[70,189],"(LC),":[71],"or":[72,194],"target":[77],"energy":[78,83],"long-term":[81],"average":[82],"speech.":[85,199],"Results":[86],"show":[87],"that:":[88],"(i)":[89],"Akin":[90],"human":[92,144,193],"recognition,":[94],"masking":[96],"can":[97],"significantly":[98],"even":[101],"when":[102],"is":[106,122,155,157,163,176],"as":[107,109,167,169],"low":[108],"-60":[110],"dB.":[111],"(ii)":[112],"The":[113,132,148],"difference":[114],"between":[115],"LC":[117,149],"more":[123],"correlated":[124],"accuracy":[128],"than":[129,159],"LC.":[130],"(iii)":[131],"performance":[133,154],"profiles":[134],"qualitatively":[138],"similar":[139],"those":[141],"obtained":[142,156],"for":[143],"recognition.":[146],"(iv)":[147],"at":[150],"which":[151,162],"peak":[153],"lower":[158],"0":[160],"dB,":[161],"optimal":[165,188],"far":[168],"gain":[172,183],"processed":[174],"concerned.":[177],"This":[178],"indicates":[179],"maximizing":[181],"may":[184],"not":[185],"be":[186],"machine":[195]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}