{"id":"https://openalex.org/W2606292126","doi":"https://doi.org/10.1109/hscma.2017.7895556","title":"An improved uncertainty decoding scheme with weighted samples for multi-channel DNN-HMM hybrid systems","display_name":"An improved uncertainty decoding scheme with weighted samples for multi-channel DNN-HMM hybrid systems","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2606292126","doi":"https://doi.org/10.1109/hscma.2017.7895556","mag":"2606292126"},"language":"en","primary_location":{"id":"doi:10.1109/hscma.2017.7895556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2017.7895556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Hands-free Speech Communications and Microphone Arrays (HSCMA)","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/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":true,"raw_author_name":"Christian Huemmer","raw_affiliation_strings":["Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Germany"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, 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":[],"is_corresponding":false,"raw_author_name":"Ramon Fernandez Astudillo","raw_affiliation_strings":["INESC-ID-Lisboa, Portugal, Unbabel Inc"],"affiliations":[{"raw_affiliation_string":"INESC-ID-Lisboa, Portugal, Unbabel Inc","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, Germany"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications and Signal Processing, University of Erlangen-Nuremberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039041764"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02642655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"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":0.9998999834060669,"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":0.9991000294685364,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.829562246799469},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7355654239654541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947534680366516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5449196100234985},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49234187602996826},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48884910345077515},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48542770743370056},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45761623978614807},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44428056478500366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43478211760520935},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43347224593162537},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3353347182273865},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06990644335746765}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.829562246799469},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7355654239654541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947534680366516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5449196100234985},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49234187602996826},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48884910345077515},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48542770743370056},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45761623978614807},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44428056478500366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43478211760520935},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43347224593162537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3353347182273865},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06990644335746765},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hscma.2017.7895556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2017.7895556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Hands-free Speech Communications and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1524333225","https://openalex.org/W1571447047","https://openalex.org/W1754457604","https://openalex.org/W1963783625","https://openalex.org/W1974036260","https://openalex.org/W1981817333","https://openalex.org/W1984541135","https://openalex.org/W1989314204","https://openalex.org/W1989549063","https://openalex.org/W2045607566","https://openalex.org/W2062164080","https://openalex.org/W2063291689","https://openalex.org/W2087006792","https://openalex.org/W2097427452","https://openalex.org/W2117518720","https://openalex.org/W2144121180","https://openalex.org/W2147706354","https://openalex.org/W2158289097","https://openalex.org/W2160306971","https://openalex.org/W2162042984","https://openalex.org/W2166547995","https://openalex.org/W2295119550","https://openalex.org/W2394967684","https://openalex.org/W2396825535","https://openalex.org/W2397761413","https://openalex.org/W2402467380","https://openalex.org/W2403021744","https://openalex.org/W2403445744","https://openalex.org/W2584063687","https://openalex.org/W3124056356","https://openalex.org/W6631362777","https://openalex.org/W6637567912","https://openalex.org/W6684010798","https://openalex.org/W6697090674","https://openalex.org/W6711908631","https://openalex.org/W6712800293","https://openalex.org/W6713273328","https://openalex.org/W6732766861"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W50892825"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,56],"improve":[4],"a":[5,37,58,67,76,99],"recently-proposed":[6],"uncertainty":[7,29,125],"decoding":[8,30,126],"scheme":[9],"for":[10,81],"DNN-HMM":[11,100,119],"(deep":[12],"neural":[13],"network":[14],"-":[15],"hidden":[16],"Markov":[17],"model)":[18],"hybrid":[19,101,120],"systems,":[20],"which":[21],"models":[22],"acoustic":[23],"features":[24],"as":[25],"random":[26],"variables.":[27],"This":[28],"strategy":[31],"averages":[32],"DNN":[33],"outputs":[34],"produced":[35],"by":[36,123],"finite":[38],"set":[39],"of":[40,48,61,106,117],"feature":[41],"samples":[42],"to":[43,75],"approximate":[44],"the":[45,49,93,107,114,118,129,136],"posterior":[46],"likelihoods":[47],"context-dependent":[50],"HMM":[51],"states.":[52],"As":[53],"main":[54],"innovation,":[55],"propose":[57],"weighted":[59,131],"(instead":[60],"arithmetic)":[62],"DNN-output":[63,132],"averaging":[64,133],"based":[65],"on":[66,92],"minimum":[68],"classification":[69],"error":[70,138],"criterion":[71],"and":[72,127],"apply":[73],"it":[74],"new":[77],"probabilistic":[78],"distortion":[79],"model":[80],"multi-channel":[82],"front-end":[83],"signal":[84],"enhancement":[85],"schemes.":[86],"The":[87],"experimental":[88],"evaluation":[89],"is":[90,111],"performed":[91],"8-channel":[94],"REVERB":[95],"Challenge":[96],"task":[97],"using":[98],"system":[102,121],"with":[103],"spatial":[104],"filtering":[105],"microphone":[108],"signals.":[109],"It":[110],"shown":[112],"that":[113,128],"recognition":[115],"accuracy":[116],"improves":[122],"incorporating":[124],"proposed":[130],"further":[134],"reduces":[135],"word":[137],"rate":[139],"scores.":[140]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}