{"id":"https://openalex.org/W2666853132","doi":"https://doi.org/10.1109/icassp.2017.7953082","title":"Combination strategy based on relative performance monitoring for multi-stream reverberant speech recognition","display_name":"Combination strategy based on relative performance monitoring for multi-stream reverberant speech recognition","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2666853132","doi":"https://doi.org/10.1109/icassp.2017.7953082","mag":"2666853132"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5011297325","display_name":"Feifei Xiong","orcid":"https://orcid.org/0000-0001-9783-2169"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Feifei Xiong","raw_affiliation_strings":["Cluster of Excellence Hearing4all, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Cluster of Excellence Hearing4all, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027797344","display_name":"Stefan Goetze","orcid":"https://orcid.org/0000-0003-1044-7343"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Goetze","raw_affiliation_strings":["Cluster of Excellence Hearing4all, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Cluster of Excellence Hearing4all, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011297325"],"corresponding_institution_ids":["https://openalex.org/I4210144375"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06639428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4870","last_page":"4874"},"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":0.9997000098228455,"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":0.9984999895095825,"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":0.8039069771766663},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7210811972618103},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6267744898796082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6081002950668335},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5729873776435852},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5531231760978699},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4806148409843445},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4620454013347626},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4334760010242462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41992995142936707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3663570284843445},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11443841457366943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09255197644233704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039069771766663},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7210811972618103},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6267744898796082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6081002950668335},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5729873776435852},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5531231760978699},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4806148409843445},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4620454013347626},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4334760010242462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41992995142936707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3663570284843445},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11443841457366943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09255197644233704},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2017.7953082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:160878","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/397492","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/397492","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W86999225","https://openalex.org/W144554552","https://openalex.org/W158407117","https://openalex.org/W173561343","https://openalex.org/W1552701380","https://openalex.org/W1820182450","https://openalex.org/W1904457459","https://openalex.org/W1984746632","https://openalex.org/W1989314204","https://openalex.org/W1993721840","https://openalex.org/W1995400204","https://openalex.org/W2048741136","https://openalex.org/W2075754845","https://openalex.org/W2096215262","https://openalex.org/W2103621378","https://openalex.org/W2130722890","https://openalex.org/W2137644731","https://openalex.org/W2153723410","https://openalex.org/W2158275940","https://openalex.org/W2160815625","https://openalex.org/W2246804954","https://openalex.org/W2289394825","https://openalex.org/W2289690552","https://openalex.org/W2399383297","https://openalex.org/W2403021744","https://openalex.org/W6603535823","https://openalex.org/W6605923411","https://openalex.org/W6606465599","https://openalex.org/W6607114211","https://openalex.org/W6690787589","https://openalex.org/W6712800293","https://openalex.org/W6713003356"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W2523437662","https://openalex.org/W2944691285","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456","https://openalex.org/W2766585573"],"abstract_inverted_index":{"A":[0],"multi-stream":[1,134],"framework":[2],"with":[3,19],"deep":[4],"neural":[5],"network":[6],"(DNN)":[7],"classifiers":[8],"is":[9,48,73,136],"applied":[10],"to":[11,30,60,65,75,79,91,104],"improve":[12],"automatic":[13],"speech":[14],"recognition":[15],"(ASR)":[16],"in":[17,58,89,138],"environments":[18,144],"different":[20],"reverberation":[21],"characteristics.":[22],"We":[23],"propose":[24],"a":[25,32,52,100],"room":[26],"parameter":[27],"estimation":[28],"model":[29,47,71],"establish":[31],"reliable":[33],"combination":[34,124],"strategy":[35],"which":[36],"performs":[37],"on":[38,127],"either":[39],"DNN":[40],"posterior":[41],"probabilities":[42],"or":[43],"word":[44,110],"lattices.":[45],"The":[46],"implemented":[49],"by":[50,121],"training":[51],"multilayer":[53],"perceptron":[54],"incorporating":[55],"auditory-inspired":[56],"features":[57],"order":[59],"distinguish":[61],"between":[62,82],"and":[63,69,116,129,140],"generalize":[64],"various":[66],"reverberant":[67,143],"conditions,":[68],"the":[70,122,133],"output":[72],"shown":[74],"be":[76],"highly":[77],"correlated":[78],"ASR":[80,135],"performances":[81],"multiple":[83],"streams,":[84],"i.e.,":[85],"relative":[86,109],"performance":[87,97],"monitoring,":[88],"contrast":[90],"conventional":[92],"mean":[93],"temporal":[94],"distance":[95],"based":[96],"monitoring":[98],"for":[99],"single":[101],"stream.":[102],"Compared":[103],"traditional":[105],"multi-condition":[106],"training,":[107],"average":[108],"error":[111],"rate":[112],"improvements":[113],"of":[114],"7.7%":[115],"9.4%":[117],"have":[118],"been":[119],"achieved":[120],"proposed":[123],"strategies":[125],"performing":[126],"posteriors":[128],"lattices,":[130],"respectively,":[131],"when":[132],"tested":[137],"known":[139],"unknown":[141],"simulated":[142],"as":[145,147],"well":[146],"realistically":[148],"recorded":[149],"conditions":[150],"taken":[151],"from":[152],"REVERB":[153],"Challenge":[154],"evaluation":[155],"set.":[156]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}