{"id":"https://openalex.org/W2151589456","doi":"https://doi.org/10.1109/icassp.2011.5947596","title":"Robust speaker identification using a CASA front-end","display_name":"Robust speaker identification using a CASA front-end","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2151589456","doi":"https://doi.org/10.1109/icassp.2011.5947596","mag":"2151589456"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947596","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/A5102205042","display_name":"Xiaojia Zhao","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":"Xiaojia Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yang Shao","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, 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":["Ohio State University, Columbus, OH, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, OH, US","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":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5468","last_page":"5471"},"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":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9987999796867371,"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/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.8544324636459351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7732741832733154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7489272356033325},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6956579685211182},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6351709365844727},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5737208724021912},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5167617201805115},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5113376975059509},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5027058124542236},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4991738796234131},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.47527876496315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4745545983314514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4482927620410919},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4428299069404602},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44147807359695435},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44145384430885315},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4384397864341736},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.415240615606308},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3267894387245178},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20518901944160461},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11714616417884827},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06507214903831482}],"concepts":[{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.8544324636459351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7732741832733154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489272356033325},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6956579685211182},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6351709365844727},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5737208724021912},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5167617201805115},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5113376975059509},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5027058124542236},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4991738796234131},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.47527876496315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4745545983314514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4482927620410919},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4428299069404602},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44147807359695435},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44145384430885315},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4384397864341736},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.415240615606308},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3267894387245178},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20518901944160461},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11714616417884827},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06507214903831482},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947596","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:10.1.1.368.1063","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.1063","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/ZSW.icassp11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W2027804983","https://openalex.org/W2055246866","https://openalex.org/W2102346872","https://openalex.org/W2122982914","https://openalex.org/W2128202590","https://openalex.org/W2142328794","https://openalex.org/W2143855671","https://openalex.org/W2147442641","https://openalex.org/W2152131029","https://openalex.org/W2561557072","https://openalex.org/W2951920181","https://openalex.org/W3021396111","https://openalex.org/W4233392025","https://openalex.org/W4256399001","https://openalex.org/W6675700563","https://openalex.org/W6680713633","https://openalex.org/W6681846431"],"related_works":["https://openalex.org/W2362704157","https://openalex.org/W3199891340","https://openalex.org/W133022121","https://openalex.org/W1567098080","https://openalex.org/W2550493152","https://openalex.org/W2345846362","https://openalex.org/W1578900076","https://openalex.org/W2294106860","https://openalex.org/W2517450235","https://openalex.org/W2061140267"],"abstract_inverted_index":{"Speaker":[0],"recognition":[1],"remains":[2],"a":[3,23,31,81,103],"challenging":[4],"task":[5],"under":[6,47,102],"noisy":[7,48,53],"conditions.":[8,49,108],"Inspired":[9],"by":[10,21,68],"auditory":[11,14],"perception,":[12],"computational":[13],"scene":[15],"analysis":[16],"(CASA)":[17],"typically":[18],"segregates":[19],"speech":[20],"producing":[22],"binary":[24],"time-frequency":[25],"mask.":[26,71],"We":[27,76],"first":[28],"show":[29],"that":[30],"recently":[32],"introduced":[33],"speaker":[34,45],"feature,":[35],"Gammatone":[36],"Frequency":[37],"Cepstral":[38],"Coefficient,":[39],"performs":[40],"substantially":[41],"better":[42],"than":[43],"conventional":[44],"features":[46],"To":[50],"deal":[51],"with":[52],"speech,":[54],"we":[55],"apply":[56],"CASA":[57,70],"separation":[58],"and":[59],"then":[60],"either":[61],"reconstruct":[62],"or":[63],"marginalize":[64],"corrupted":[65],"components":[66],"indicated":[67],"the":[69,86],"Both":[72],"methods":[73],"are":[74],"effective.":[75],"further":[77],"combine":[78],"them":[79],"into":[80],"single":[82],"system":[83,94],"depending":[84],"on":[85],"detected":[87],"signal":[88],"to":[89],"noise":[90],"ratio":[91],"(SNR).":[92],"This":[93],"achieves":[95],"significant":[96],"performance":[97],"improvements":[98],"over":[99],"related":[100],"systems":[101],"wide":[104],"range":[105],"of":[106],"SNR":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"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"}