{"id":"https://openalex.org/W2397761413","doi":"https://doi.org/10.1109/icassp.2016.7472781","title":"A new uncertainty decoding scheme for DNN-HMM hybrid systems with multichannel speech enhancement","display_name":"A new uncertainty decoding scheme for DNN-HMM hybrid systems with multichannel speech enhancement","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2397761413","doi":"https://doi.org/10.1109/icassp.2016.7472781","mag":"2397761413"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5039041764","display_name":"Christian Huemmer","orcid":"https://orcid.org/0000-0002-4341-4217"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Huemmer","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015722753","display_name":"Andreas Schwarz","orcid":"https://orcid.org/0000-0001-5484-3976"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Schwarz","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018357812","display_name":"Hendrik Barfuss","orcid":"https://orcid.org/0000-0001-7510-7660"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hendrik Barfuss","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"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":[],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Ramon Fernandez Astudillo","raw_affiliation_strings":["Spoken Language Systems Laboratory, Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Laboratory, Lisboa, Portugal","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068787682","display_name":"Walter Kellermann","orcid":"https://orcid.org/0000-0002-6501-3174"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Walter Kellermann","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.397,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":7,"citation_normalized_percentile":{"value":0.603923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":83,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"5760","last_page":"5764"},"is_retracted":false,"is_paratext":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":0.9997,"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":0.9978,"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/feature","display_name":"Feature (linguistics)","score":0.61055076},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.52915716}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.76795185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969627},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6680424},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.61055076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5916668},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5801302},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.53526783},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.52915716},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.51586574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4915472},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4284067},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.41491646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25077337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16868317},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1508381},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":23,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1754457604","https://openalex.org/W1931312565","https://openalex.org/W1969838670","https://openalex.org/W1989314204","https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2039716246","https://openalex.org/W2046317813","https://openalex.org/W2117518720","https://openalex.org/W2146324387","https://openalex.org/W2147706354","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2162042984","https://openalex.org/W2166547995","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2394967684","https://openalex.org/W2402467380","https://openalex.org/W2403445744","https://openalex.org/W2584063687","https://openalex.org/W3124056356"],"related_works":["https://openalex.org/W3145575561","https://openalex.org/W2905188205","https://openalex.org/W2396048001","https://openalex.org/W2364370872","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2001275470","https://openalex.org/W1559044324"],"abstract_inverted_index":{"Uncertainty":[0],"decoding":[1,129],"combines":[2],"a":[3,12,31,54,61,85,93,108,140],"probabilistic":[4],"feature":[5,35,66,102,112],"description":[6],"with":[7,53],"the":[8,26,74,118,123,136,145],"acoustic":[9],"model":[10],"of":[11,34,84,111,114,139],"speech":[13,56],"recognition":[14,137],"system.":[15,58],"For":[16],"DNN-HMM":[17,141],"hybrid":[18,142],"systems,":[19],"this":[20,44,48,126],"can":[21],"be":[22],"realized":[23],"by":[24,30],"averaging":[25],"DNN":[27,120],"outputs":[28],"produced":[29],"finite":[32,109],"set":[33,110],"samples":[36,67],"(drawn":[37],"from":[38,68],"an":[39,100],"estimated":[40],"probability":[41],"distribution).":[42],"In":[43,122],"article,":[45],"we":[46,116],"employ":[47],"sampling":[49],"approach":[50],"in":[51],"combination":[52],"multi-microphone":[55],"enhancement":[57,95],"We":[59],"propose":[60],"new":[62,127],"strategy":[63,130],"for":[64,144],"generating":[65],"multichannel":[69],"signals,":[70],"based":[71],"on":[72],"modeling":[73],"spatial":[75],"coherence":[76,91],"estimates":[77],"between":[78],"different":[79],"microphone":[80],"pairs":[81],"as":[82],"realizations":[83],"latent":[86],"random":[87],"variable.":[88],"From":[89],"each":[90],"estimate,":[92],"spectral":[94],"gain":[96],"is":[97,104,131],"computed":[98],"and":[99],"enhanced":[101],"vector":[103],"obtained,":[105],"thus":[106],"producing":[107],"samples,":[113],"which":[115],"average":[117],"respective":[119],"outputs.":[121],"experimental":[124],"part,":[125],"uncertainty":[128],"shown":[132],"to":[133],"consistently":[134],"improve":[135],"accuracy":[138],"system":[143],"8-channel":[146],"REVERB":[147],"Challenge":[148],"task.":[149]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2397761413","counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-01-02T08:46:09.901684","created_date":"2016-06-24"}