{"id":"https://openalex.org/W2620087116","doi":"https://doi.org/10.1109/icassp.2017.7953158","title":"On DNN posterior probability combination in multi-stream speech recognition for reverberant environments","display_name":"On DNN posterior probability combination in multi-stream speech recognition for reverberant environments","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2620087116","doi":"https://doi.org/10.1109/icassp.2017.7953158","mag":"2620087116"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953158","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/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]},{"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","Fraunhofer Institute for Digital Media Technology IDMT, Speech and Audio Technology (HSA), Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Cluster of Excellence Hearing4all, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375"]},{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT, Speech and Audio Technology (HSA), Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"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/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]},{"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","Fraunhofer Institute for Digital Media Technology IDMT, Speech and Audio Technology (HSA), Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Cluster of Excellence Hearing4all, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375"]},{"raw_affiliation_string":"Fraunhofer Institute for Digital Media Technology IDMT, Speech and Audio Technology (HSA), Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"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/I4210138578","https://openalex.org/I4210144375"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04977869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"5250","last_page":"5254"},"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":0.9998000264167786,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912886142730713},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6960347890853882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.648751974105835},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5764760971069336},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5665071606636047},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5417402982711792},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5304229855537415},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.522112250328064},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.49001041054725647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43837660551071167},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4293597340583801},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39157384634017944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09239038825035095},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08671152591705322},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.07267129421234131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912886142730713},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6960347890853882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.648751974105835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5764760971069336},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5665071606636047},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5417402982711792},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5304229855537415},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.522112250328064},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.49001041054725647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43837660551071167},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4293597340583801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39157384634017944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09239038825035095},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08671152591705322},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.07267129421234131},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2017.7953158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953158","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:160877","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/397494","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/397494","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W144554552","https://openalex.org/W197151588","https://openalex.org/W1524333225","https://openalex.org/W1552701380","https://openalex.org/W1820182450","https://openalex.org/W1904457459","https://openalex.org/W1984746632","https://openalex.org/W1989314204","https://openalex.org/W1993882792","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/W4300402905","https://openalex.org/W6605923411","https://openalex.org/W6607944266","https://openalex.org/W6631362777","https://openalex.org/W6690787589","https://openalex.org/W6713003356"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W2523437662","https://openalex.org/W89844371","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456","https://openalex.org/W2136232598"],"abstract_inverted_index":{"A":[0],"multi-stream":[1,100],"framework":[2],"with":[3,24,45,86],"deep":[4],"neural":[5],"network":[6],"(DNN)":[7],"classifiers":[8],"has":[9],"been":[10],"applied":[11],"in":[12,22,73,102],"this":[13],"paper":[14],"to":[15,35,63],"improve":[16],"automatic":[17],"speech":[18],"recognition":[19],"(ASR)":[20],"performance":[21],"environments":[23,77],"different":[25,103],"reverberation":[26],"characteristics.":[27],"We":[28],"propose":[29],"a":[30,60],"room":[31],"parameter":[32],"estimation":[33],"model":[34,55],"determine":[36],"the":[37,46],"stream":[38],"weights":[39],"for":[40,52],"DNN":[41],"posterior":[42],"probability":[43],"combination":[44],"aim":[47],"of":[48,93],"obtaining":[49],"reliable":[50],"log-likelihoods":[51],"decoding.":[53],"The":[54,69],"is":[56,71],"implemented":[57],"by":[58],"training":[59],"multi-layer":[61],"perceptron":[62],"distinguish":[64],"between":[65],"various":[66],"reverberant":[67,104],"environments.":[68],"method":[70],"tested":[72],"known":[74],"and":[75,84,95],"unknown":[76],"against":[78],"approaches":[79],"based":[80],"on":[81],"inverse":[82],"entropy":[83],"autoencoders,":[85],"average":[87],"relative":[88],"word":[89],"error":[90],"rate":[91],"improvements":[92],"46%":[94],"29%,":[96],"respectively,":[97],"when":[98],"performing":[99],"ASR":[101],"situations.":[105]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}