{"id":"https://openalex.org/W2106587885","doi":"https://doi.org/10.1109/icassp.2012.6288954","title":"Inventory-style speech enhancement with uncertainty-of-observation techniques","display_name":"Inventory-style speech enhancement with uncertainty-of-observation techniques","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2106587885","doi":"https://doi.org/10.1109/icassp.2012.6288954","mag":"2106587885"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5075524022","display_name":"Robert M. Nickel","orcid":"https://orcid.org/0009-0005-5007-5355"},"institutions":[{"id":"https://openalex.org/I131221577","display_name":"Bucknell University","ror":"https://ror.org/00fc1qt65","country_code":"US","type":"education","lineage":["https://openalex.org/I131221577"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R. M. Nickel","raw_affiliation_strings":["Department of Electrical Engineering, Bucknell University, Lewisburg, PA, USA","Department of Electrical Engineering, Bucknell University, Lewisburg, PA 17837, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Bucknell University, Lewisburg, PA, USA","institution_ids":["https://openalex.org/I131221577"]},{"raw_affiliation_string":"Department of Electrical Engineering, Bucknell University, Lewisburg, PA 17837, USA","institution_ids":["https://openalex.org/I131221577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003156858","display_name":"Ram\u00f3n Fern\u00e1ndez Astudillo","orcid":"https://orcid.org/0000-0001-9443-2346"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"R. F. Astudillo","raw_affiliation_strings":["Spoken Language Systems Laboratory, INESC-ID Lisboa, Lisboa, Portugal","INESC-ID Lisboa, Spoken Language Systems Lab, R. Alves Redol 9, 1000-029, Portugal"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Laboratory, INESC-ID Lisboa, Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"INESC-ID Lisboa, Spoken Language Systems Lab, R. Alves Redol 9, 1000-029, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Kolossa","raw_affiliation_strings":["Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr Universit\u00e4t Bochum, Bochum, Germany","Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr-Universit\u00e4t Bochum, 44780, Germany"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr Universit\u00e4t Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr-Universit\u00e4t Bochum, 44780, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046724251","display_name":"Steffen Zeiler","orcid":"https://orcid.org/0009-0002-9594-2633"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Zeiler","raw_affiliation_strings":["Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr Universit\u00e4t Bochum, Bochum, Germany","Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr-Universit\u00e4t Bochum, 44780, Germany"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr Universit\u00e4t Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr-Universit\u00e4t Bochum, 44780, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064880163","display_name":"Rainer Martin","orcid":"https://orcid.org/0000-0002-9587-4215"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"R. Martin","raw_affiliation_strings":["Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr Universit\u00e4t Bochum, Bochum, Germany","Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr-Universit\u00e4t Bochum, 44780, Germany"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr Universit\u00e4t Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"Institut f\u00fcr Kommunikationsakustik, ID 2/231, Ruhr-Universit\u00e4t Bochum, 44780, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075524022"],"corresponding_institution_ids":["https://openalex.org/I131221577"],"apc_list":null,"apc_paid":null,"fwci":0.9794,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7974415,"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":"4645","last_page":"4648"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.7365902662277222},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7187018394470215},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6997723579406738},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6751440763473511},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6337948441505432},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6126921772956848},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5554733872413635},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5478779673576355},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4939332604408264},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4808831512928009},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46151280403137207},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4354126453399658},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3844480514526367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38202640414237976},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0928405225276947},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07754704356193542},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07562506198883057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365902662277222},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7187018394470215},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6997723579406738},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6751440763473511},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6337948441505432},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6126921772956848},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5554733872413635},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5478779673576355},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4939332604408264},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4808831512928009},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46151280403137207},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4354126453399658},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3844480514526367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38202640414237976},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0928405225276947},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07754704356193542},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07562506198883057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"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":12,"referenced_works":["https://openalex.org/W350343755","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1556051766","https://openalex.org/W2141998673","https://openalex.org/W2145475542","https://openalex.org/W2168348268","https://openalex.org/W2171992722","https://openalex.org/W2256662675","https://openalex.org/W4245919820","https://openalex.org/W6611706912","https://openalex.org/W6633447613"],"related_works":["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","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172"],"abstract_inverted_index":{"We":[0],"present":[1,111],"a":[2,21,26,112],"new":[3,74,113,132],"method":[4,114,133],"for":[5,123],"inventory-style":[6],"speech":[7,23,31],"enhancement":[8,17],"that":[9,40,56,115,130],"significantly":[10],"improves":[11],"over":[12],"earlier":[13,143],"approaches":[14,144],"[1].":[15,106],"Inventory-style":[16],"attempts":[18],"to":[19,45,119,138],"resynthesize":[20],"clean":[22],"signal":[24,28,50],"from":[25],"noisy":[27],"via":[29],"corpus-based":[30],"synthesis.":[32],"The":[33],"advantage":[34],"of":[35,72,86,97],"such":[36],"an":[37],"approach":[38],"is":[39,42,67,134],"one":[41],"not":[43,135],"bound":[44],"trade":[46],"noise":[47,100,124],"suppression":[48],"against":[49],"distortion":[51],"in":[52,64,145],"the":[53,69,84,98,103,121,131,142],"same":[54],"way":[55],"most":[57],"traditional":[58],"methods":[59,92],"do.":[60],"A":[61],"significant":[62],"improvement":[63],"perceptual":[65,146],"quality":[66],"typically":[68],"result.":[70],"Disadvantages":[71],"this":[73,108],"approach,":[75],"however,":[76],"include":[77],"speaker":[78],"dependency,":[79],"increased":[80],"processing":[81],"delays,":[82],"and":[83],"necessity":[85],"substantial":[87],"system":[88],"training.":[89,126],"Earlier":[90],"published":[91],"relied":[93],"on":[94],"a-priori":[95],"knowledge":[96],"expected":[99],"type":[101],"during":[102],"training":[104],"process":[105],"In":[107],"paper":[109],"we":[110],"exploits":[116],"uncertainty-of-observation":[117],"techniques":[118],"circumvent":[120],"need":[122],"specific":[125],"Experimental":[127],"results":[128],"show":[129],"only":[136],"able":[137],"match,":[139],"but":[140],"outperform":[141],"quality.":[147]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
