{"id":"https://openalex.org/W1999736059","doi":"https://doi.org/10.1109/icassp.2014.6854777","title":"A structure-preserving training target for supervised speech separation","display_name":"A structure-preserving training target for supervised speech separation","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1999736059","doi":"https://doi.org/10.1109/icassp.2014.6854777","mag":"1999736059"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100375981","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-3060-4345"},"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":"Yuxuan Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, 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/A5100375981"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.9113,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91273148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6107","last_page":"6111"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9990000128746033,"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/discriminative-model","display_name":"Discriminative model","score":0.8559274077415466},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.7958922982215881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6819173097610474},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6469792127609253},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6018040180206299},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5758975744247437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5331549048423767},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5130361318588257},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49651724100112915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4787853956222534},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.4732961058616638},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4579964280128479},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43648761510849},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.32752925157546997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30878734588623047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2421639859676361},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11124855279922485}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8559274077415466},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.7958922982215881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6819173097610474},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6469792127609253},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6018040180206299},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5758975744247437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5331549048423767},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5130361318588257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49651724100112915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4787853956222534},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.4732961058616638},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4579964280128479},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43648761510849},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32752925157546997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30878734588623047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2421639859676361},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11124855279922485},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854777","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1552314771","https://openalex.org/W1814328102","https://openalex.org/W1963970749","https://openalex.org/W1989364685","https://openalex.org/W2027701650","https://openalex.org/W2027804983","https://openalex.org/W2047919706","https://openalex.org/W2057200980","https://openalex.org/W2087126002","https://openalex.org/W2122982914","https://openalex.org/W2124149378","https://openalex.org/W2131753991","https://openalex.org/W2141411743","https://openalex.org/W2141520175","https://openalex.org/W2141998673","https://openalex.org/W2146502635","https://openalex.org/W2158291955","https://openalex.org/W2561557072","https://openalex.org/W4231807801","https://openalex.org/W6638523313","https://openalex.org/W6681435938"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2028846388","https://openalex.org/W4295210860","https://openalex.org/W2072015625","https://openalex.org/W2128027845","https://openalex.org/W2117955483"],"abstract_inverted_index":{"Supervised":[0],"learning":[1],"based":[2],"speech":[3],"separation":[4],"has":[5],"shown":[6],"considerable":[7],"success":[8],"recently.":[9],"In":[10,53,117],"its":[11],"simplest":[12],"form,":[13],"a":[14,20,72,130],"discriminative":[15,121],"model":[16,49,74,122,132],"is":[17,28,63,82,123],"trained":[18],"as":[19,35],"time-frequency":[21],"masking":[22],"function,":[23],"where":[24],"the":[25,36,76,86,93,101,114,120,127,134,149],"training":[26,60,151],"target":[27,61,135],"an":[29,58],"ideal":[30,37,78,94],"mask.":[31],"Ideal":[32],"masks,":[33,39],"such":[34],"binary":[38],"are":[40,109],"structured":[41],"spectro-temporal":[42,106],"patterns.":[43],"However,":[44],"previous":[45],"formulations":[46],"do":[47],"not":[48],"prominent":[50],"output":[51],"structure.":[52,68],"this":[54],"paper,":[55],"we":[56,97],"propose":[57],"alternative":[59],"that":[62,81],"explicitly":[64],"related":[65,84],"to":[66,85,99,112,125],"mask":[67,80,95],"We":[69],"first":[70],"learn":[71,98],"compositional":[73],"of":[75,90,129,133,136],"square-root":[77],"ratio":[79],"closely":[83],"Wiener":[87],"filter.":[88],"Instead":[89],"directly":[91],"estimating":[92],"values,":[96],"predict":[100,126],"weights":[102],"for":[103],"resulting":[104],"mask-level":[105],"bases,":[107],"which":[108],"then":[110],"used":[111,124],"generate":[113],"estimated":[115],"masks.":[116],"other":[118],"words,":[119],"parameters":[128],"generative":[131],"interest.":[137],"Experimental":[138],"results":[139],"show":[140],"consistent":[141],"improvements":[142],"in":[143],"low":[144],"SNR":[145],"conditions":[146],"by":[147],"adopting":[148],"new":[150],"target.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}