{"id":"https://openalex.org/W2405206884","doi":"https://doi.org/10.21437/interspeech.2014-582","title":"Speech enhancement by low-rank and convolutive dictionary spectrogram decomposition","display_name":"Speech enhancement by low-rank and convolutive dictionary spectrogram decomposition","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2405206884","doi":"https://doi.org/10.21437/interspeech.2014-582","mag":"2405206884"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5106557560","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-8483-1578"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010404092","display_name":"Brian McFee","orcid":"https://orcid.org/0000-0001-6261-9747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian McFee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel P. W. Ellis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106557560"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.8734,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76898148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9995999932289124,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9995999932289124,"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/spectrogram","display_name":"Spectrogram","score":0.8590331673622131},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7636292576789856},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7354681491851807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7118182182312012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694965124130249},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6275302171707153},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5778583288192749},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5360308885574341},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.48672249913215637},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41143715381622314},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37877029180526733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33638811111450195},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27817848324775696},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20867252349853516},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06675896048545837}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8590331673622131},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7636292576789856},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7354681491851807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7118182182312012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694965124130249},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6275302171707153},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5778583288192749},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5360308885574341},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.48672249913215637},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41143715381622314},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37877029180526733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33638811111450195},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27817848324775696},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20867252349853516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06675896048545837},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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.2014-582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1980687383","https://openalex.org/W2001987918","https://openalex.org/W2121973264","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2130855892","https://openalex.org/W2145962650","https://openalex.org/W2151484683","https://openalex.org/W2164098335","https://openalex.org/W2401258970","https://openalex.org/W2407530971","https://openalex.org/W2913535645","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W1975881626","https://openalex.org/W2089240210","https://openalex.org/W4252208810","https://openalex.org/W4375869276","https://openalex.org/W1585241115"],"abstract_inverted_index":{"A":[0],"successful":[1],"speech":[2,10,42,91,102,120,140],"enhancement":[3,43],"system":[4],"requires":[5,64],"strong":[6],"models":[7],"for":[8],"both":[9],"and":[11,56,70,103,130,141],"noise":[12,25,55,69,77],"to":[13,122,143],"decompose":[14],"a":[15,41,57,127],"mixture":[16],"into":[17,51],"the":[18,24,30,48,68,76,85,89,111,116,119,124,139],"most":[19],"likely":[20],"combination.":[21],"However,":[22,74],"if":[23],"encountered":[26],"differs":[27],"significantly":[28],"from":[29],"system\u2019s":[31],"assumptions,":[32],"performance":[33],"will":[34],"suffer.":[35],"In":[36,106],"previous":[37,112],"work,":[38,108],"we":[39,109],"proposed":[40],"framework":[44],"based":[45],"on":[46],"decomposing":[47],"noisy":[49,90,149],"spectrogram":[50],"low":[52],"rank":[53],"background":[54,104],"sparse":[58,128],"activation":[59,129],"of":[60,88,118,126],"prelearned":[61],"templates,":[62],"which":[63,134],"few":[65],"assumptions":[66],"about":[67],"showed":[71],"promising":[72],"results.":[73],"when":[75],"is":[78],"highly":[79,147],"non-stationary":[80],"or":[81],"has":[82],"large":[83],"amplitude,":[84],"local":[86],"SNR":[87],"can":[92],"change":[93],"drastically,":[94],"resulting":[95],"in":[96,146],"less":[97],"accurate":[98],"decompositions":[99],"between":[100],"foreground":[101],"noise.":[105],"this":[107],"extend":[110],"model":[113],"by":[114],"changing":[115],"modeling":[117],"part":[121],"be":[123],"convolution":[125],"pre-learned":[131],"template":[132],"patches,":[133],"enforces":[135],"continuous":[136],"structure":[137],"within":[138],"leads":[142],"better":[144],"results":[145],"corrupted":[148],"mixtures.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}