{"id":"https://openalex.org/W2962829711","doi":"https://doi.org/10.21437/interspeech.2018-83","title":"Deep Speech Denoising with Vector Space Projections","display_name":"Deep Speech Denoising with Vector Space Projections","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2962829711","doi":"https://doi.org/10.21437/interspeech.2018-83","mag":"2962829711"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-83","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-83","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5112456009","display_name":"J. W. Hetherly","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jeffrey Hetherly","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090718376","display_name":"Paul Gamble","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Gamble","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082233647","display_name":"M. A. Barrios","orcid":"https://orcid.org/0000-0001-5673-4255"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Alejandra Barrios","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080560015","display_name":"Cory Stephenson","orcid":"https://orcid.org/0000-0003-0078-6501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cory Stephenson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110791031","display_name":"Karl Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karl Ni","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112456009"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.241265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3474","last_page":"3478"},"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":0.9988999962806702,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7343622446060181},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6482595801353455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6047008037567139},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5692802667617798},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49312254786491394},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4892144203186035},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.47372928261756897},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4660884737968445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45359888672828674},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43691083788871765},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.43632039427757263},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3951323628425598},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12115105986595154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343622446060181},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6482595801353455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6047008037567139},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5692802667617798},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49312254786491394},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4892144203186035},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.47372928261756897},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4660884737968445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45359888672828674},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43691083788871765},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.43632039427757263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3951323628425598},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12115105986595154},{"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-83","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-83","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1973681148","https://openalex.org/W2013608223","https://openalex.org/W2038484192","https://openalex.org/W2069681747","https://openalex.org/W2132304835","https://openalex.org/W2150415460","https://openalex.org/W2152790380","https://openalex.org/W2221409856","https://openalex.org/W2404974779","https://openalex.org/W2460742184","https://openalex.org/W2463355599","https://openalex.org/W2471801048","https://openalex.org/W2519091744","https://openalex.org/W2533545350","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2563106974","https://openalex.org/W2605138598","https://openalex.org/W2962715207","https://openalex.org/W2997574889","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2396048001","https://openalex.org/W2905188205","https://openalex.org/W1559044324","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W3108403339"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2],"algorithm":[3,165],"to":[4,149],"denoise":[5],"speakers":[6,31,34],"from":[7,32,37,53],"a":[8,50,64,123,172],"single":[9],"microphone":[10],"in":[11,57,87,111],"the":[12,23,73,104,109,112,152],"presence":[13],"of":[14,26,75,99,151],"non-stationary":[15],"and":[16,35,77,96,137,146,175],"dynamic":[17],"noise.Our":[18],"approach":[19],"is":[20,85,90,97],"inspired":[21],"by":[22,79,170],"recent":[24],"success":[25],"neural":[27],"network":[28],"models":[29],"separating":[30],"other":[33],"singers":[36],"instrumental":[38],"accompaniment.Unlike":[39],"prior":[40],"art,":[41],"we":[42],"leverage":[43],"embedding":[44,68],"spaces":[45],"produced":[46],"with":[47,117],"source-contrastive":[48],"estimation,":[49],"technique":[51],"derived":[52],"negative":[54],"sampling":[55],"techniques":[56],"natural":[58],"language":[59],"processing,":[60],"while":[61,179],"simultaneously":[62],"obtaining":[63],"continuous":[65],"inference":[66],"mask.Our":[67],"space":[69,84],"directly":[70],"optimizes":[71],"for":[72],"discrimination":[74],"speaker":[76,92,110],"noise":[78,94,129],"jointly":[80],"modeling":[81],"their":[82],"characteristics.This":[83],"generalizable":[86],"that":[88,121,127,133,139],"it":[89],"not":[91,107],"or":[93],"specific":[95],"capable":[98],"denoising":[100],"speech":[101],"even":[102],"if":[103],"model":[105],"has":[106],"seen":[108],"training":[113],"set.Parameters":[114],"are":[115],"trained":[116],"dual":[118],"objectives:":[119],"one":[120],"promotes":[122],"selective":[124],"bandpass":[125],"filter":[126],"eliminates":[128],"at":[130],"time-frequency":[131,142],"positions":[132],"exceed":[134],"signal":[135,145],"power,":[136],"another":[138],"proportionally":[140],"splits":[141],"content":[143],"between":[144],"noise.We":[147],"compare":[148],"state":[150],"art":[153],"algorithms":[154],"as":[155,157],"well":[156],"traditional":[158],"sparse":[159],"non-negative":[160],"matrix":[161],"factorization":[162],"solutions.The":[163],"resulting":[164],"avoids":[166],"severe":[167],"computational":[168],"burden":[169],"providing":[171],"more":[173],"intuitive":[174],"easily":[176],"optimized":[177],"approach,":[178],"achieving":[180],"competitive":[181],"accuracy.":[182]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}