{"id":"https://openalex.org/W2152632599","doi":"https://doi.org/10.1109/icassp.2009.4960677","title":"Learning to maximize signal-to-noise ratio for reverberant speech segregation","display_name":"Learning to maximize signal-to-noise ratio for reverberant speech segregation","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2152632599","doi":"https://doi.org/10.1109/icassp.2009.4960677","mag":"2152632599"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5025797022","display_name":"Zhaozhang Jin","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":true,"raw_author_name":"Zhaozhang Jin","raw_affiliation_strings":["Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center of Cognitive Science, 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":["Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & Center of Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025797022"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19403183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4689","last_page":"4692"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8520649075508118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479175925254822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6871785521507263},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5712738037109375},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5702820420265198},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5593210458755493},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5527820587158203},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5196422338485718},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4864804446697235},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.485429584980011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43604928255081177},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41736680269241333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3869889974594116},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23644718527793884},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20309996604919434},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11083328723907471}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8520649075508118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479175925254822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6871785521507263},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5712738037109375},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5702820420265198},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5593210458755493},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5527820587158203},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5196422338485718},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4864804446697235},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.485429584980011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43604928255081177},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41736680269241333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3869889974594116},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23644718527793884},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20309996604919434},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11083328723907471},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2009.4960677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.3465","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.3465","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/Jin-Wang.icassp09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.1067","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.1067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.epernicus.com/shared_documents/232/jin_icassp09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7799999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W10765870","https://openalex.org/W160800111","https://openalex.org/W1500551892","https://openalex.org/W1575829986","https://openalex.org/W1825077972","https://openalex.org/W2027804983","https://openalex.org/W2057662515","https://openalex.org/W2078210373","https://openalex.org/W2088805357","https://openalex.org/W2117678320","https://openalex.org/W2123157731","https://openalex.org/W2128334000","https://openalex.org/W2131470542","https://openalex.org/W2139393465","https://openalex.org/W2149425615","https://openalex.org/W2561557072","https://openalex.org/W2914048585","https://openalex.org/W2970850616","https://openalex.org/W2981666567","https://openalex.org/W3143059483","https://openalex.org/W3216401400","https://openalex.org/W4233392025","https://openalex.org/W4256399001","https://openalex.org/W6600441815","https://openalex.org/W6638473186","https://openalex.org/W6680919041","https://openalex.org/W6758698360","https://openalex.org/W6767055042","https://openalex.org/W6769316794"],"related_works":["https://openalex.org/W2621851636","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2120771489","https://openalex.org/W3110551121","https://openalex.org/W2126638480","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2161396743","https://openalex.org/W2386453889"],"abstract_inverted_index":{"Monaural":[0],"speech":[1],"segregation":[2,51],"in":[3],"reverberant":[4,65],"environments":[5],"is":[6,58],"a":[7,13,53],"very":[8,75],"difficult":[9],"problem.":[10],"We":[11],"develop":[12],"supervised":[14],"learning":[15],"approach":[16],"by":[17],"proposing":[18],"an":[19],"objective":[20,39],"function":[21,40],"that":[22],"directly":[23],"relates":[24],"to":[25,60],"the":[26],"computational":[27],"goal":[28],"of":[29],"maximizing":[30],"signal-to-noise":[31],"ratio.":[32],"The":[33],"model":[34],"trained":[35],"using":[36],"this":[37],"new":[38],"yields":[41],"significantly":[42],"better":[43],"results":[44],"for":[45],"time-frequency":[46],"unit":[47],"labeling.":[48],"In":[49],"our":[50],"system,":[52],"segmentation":[54],"and":[55,67],"grouping":[56],"framework":[57],"utilized":[59],"form":[61],"reliable":[62],"segments":[63],"under":[64],"conditions":[66],"organize":[68],"them":[69],"into":[70],"streams.":[71],"Systematic":[72],"evaluations":[73],"show":[74],"promising":[76],"results.":[77]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}