{"id":"https://openalex.org/W2012738535","doi":"https://doi.org/10.1109/icassp.2013.6639119","title":"Learning invariant features for speech separation","display_name":"Learning invariant features for speech separation","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2012738535","doi":"https://doi.org/10.1109/icassp.2013.6639119","mag":"2012738535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639119","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":"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/A5101924647","display_name":"Kun Han","orcid":"https://orcid.org/0000-0003-2148-7594"},"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":"Kun Han","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"],"raw_orcid":null,"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"]}]},{"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"],"raw_orcid":null,"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":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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"7492","last_page":"7496"},"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":0.9958000183105469,"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":0.9952999949455261,"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":0.707524299621582},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6043387055397034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.56939697265625},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5511578321456909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5447108149528503},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48623600602149963},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4617590606212616},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.46090516448020935},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4481017291545868},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.42040276527404785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41153183579444885},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.41052180528640747},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40591734647750854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19820159673690796},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.18201029300689697},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17315083742141724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707524299621582},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6043387055397034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.56939697265625},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5511578321456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5447108149528503},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48623600602149963},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4617590606212616},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.46090516448020935},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4481017291545868},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.42040276527404785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41153183579444885},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.41052180528640747},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40591734647750854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19820159673690796},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.18201029300689697},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17315083742141724},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639119","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:10.1.1.368.1518","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.1518","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/Han-Wang.icassp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1571821784","https://openalex.org/W1722318740","https://openalex.org/W1963970749","https://openalex.org/W1979099822","https://openalex.org/W1989364685","https://openalex.org/W2015469795","https://openalex.org/W2027804983","https://openalex.org/W2057889776","https://openalex.org/W2085191029","https://openalex.org/W2090923791","https://openalex.org/W2099501835","https://openalex.org/W2099904336","https://openalex.org/W2120354757","https://openalex.org/W2122922389","https://openalex.org/W2122982914","https://openalex.org/W2131753991","https://openalex.org/W2156909104","https://openalex.org/W2158602558","https://openalex.org/W2162651021","https://openalex.org/W2169495281","https://openalex.org/W2561557072","https://openalex.org/W2981666567","https://openalex.org/W3146885639","https://openalex.org/W3216401400","https://openalex.org/W4230674625","https://openalex.org/W4231807801","https://openalex.org/W4233392025","https://openalex.org/W6634082615","https://openalex.org/W6637542466","https://openalex.org/W6654520578","https://openalex.org/W6678296315","https://openalex.org/W6683661426"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W2092735486","https://openalex.org/W2156376969","https://openalex.org/W2117416982"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"on":[2],"speech":[3,14,86,126],"separation":[4,127],"show":[5,117],"that":[6,99],"the":[7,26,35,38,42,46,60,89,93,106,118,121],"ideal":[8],"binary":[9],"mask":[10],"(IBM)":[11],"substantially":[12],"improves":[13],"intelligibility":[15],"in":[16,53,88],"noise.":[17],"Supervised":[18],"learning":[19,30,81],"can":[20],"be":[21],"used":[22],"to":[23,70,76,83,102,110,112],"effectively":[24],"estimate":[25],"IBM.":[27],"However,":[28],"supervised":[29],"has":[31],"trouble":[32],"dealing":[33],"with":[34],"situations":[36],"where":[37],"probabilistic":[39],"properties":[40],"of":[41,57,120],"training":[43],"data":[44,48],"and":[45],"test":[47],"do":[49],"not":[50,68],"match,":[51],"resulting":[52],"a":[54,78],"challenging":[55],"issue":[56],"generalization":[58],"whereby":[59],"system":[61,107],"trained":[62],"under":[63],"particular":[64],"noise":[65,72,104,114],"conditions":[66],"may":[67],"generalize":[69,111],"new":[71],"conditions.":[73,115],"We":[74],"propose":[75],"use":[77],"novel":[79],"metric":[80],"method":[82],"learn":[84],"invariant":[85],"features":[87,95],"kernel":[90],"space.":[91],"As":[92],"learned":[94],"encode":[96],"speech-related":[97],"information":[98],"is":[100,108],"robust":[101],"different":[103],"types,":[105],"expected":[109],"unseen":[113],"Evaluations":[116],"advantage":[119],"proposed":[122],"approach":[123],"over":[124],"other":[125],"systems.":[128]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}