{"id":"https://openalex.org/W2986515364","doi":"https://doi.org/10.1109/icassp40776.2020.9053025","title":"Predicting Word Error Rate for Reverberant Speech","display_name":"Predicting Word Error Rate for Reverberant Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2986515364","doi":"https://doi.org/10.1109/icassp40776.2020.9053025","mag":"2986515364"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.00566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036868085","display_name":"Hannes Gamper","orcid":"https://orcid.org/0000-0002-2148-6367"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hannes Gamper","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, redmond, WA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034420214","display_name":"Dimitra Emmanouilidou","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitra Emmanouilidou","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, redmond, WA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, redmond, WA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ivan J. Tashev","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036868085"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00763208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"495"},"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":0.9995999932289124,"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":0.9977999925613403,"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/reverberation","display_name":"Reverberation","score":0.8551516532897949},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7049509882926941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6829482316970825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6701128482818604},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.5538076758384705},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5411386489868164},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5274824500083923},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.502919614315033},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4859115183353424},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4638972282409668},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41531285643577576},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28187236189842224},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2671976685523987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25065064430236816},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18465575575828552}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8551516532897949},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7049509882926941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829482316970825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6701128482818604},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.5538076758384705},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5411386489868164},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5274824500083923},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.502919614315033},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4859115183353424},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4638972282409668},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41531285643577576},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28187236189842224},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2671976685523987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25065064430236816},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18465575575828552},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.00566","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.00566","pdf_url":"https://arxiv.org/pdf/1911.00566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2986515364","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.00566","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.00566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.00566","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/tsen-6171","is_oa":true,"landing_page_url":"https://doi.org/10.17023/tsen-6171","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.00566","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.00566","pdf_url":"https://arxiv.org/pdf/1911.00566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2986515364.pdf","grobid_xml":"https://content.openalex.org/works/W2986515364.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W190060899","https://openalex.org/W1494198834","https://openalex.org/W1499999342","https://openalex.org/W1524333225","https://openalex.org/W1557831657","https://openalex.org/W1968834101","https://openalex.org/W1972896459","https://openalex.org/W1973681148","https://openalex.org/W1989314204","https://openalex.org/W2043356347","https://openalex.org/W2067805742","https://openalex.org/W2074604179","https://openalex.org/W2136682440","https://openalex.org/W2142370513","https://openalex.org/W2172491908","https://openalex.org/W2242685705","https://openalex.org/W2245569228","https://openalex.org/W2294798173","https://openalex.org/W2296434735","https://openalex.org/W2326699523","https://openalex.org/W2402003764","https://openalex.org/W2617258110","https://openalex.org/W2696967604","https://openalex.org/W2962824709","https://openalex.org/W2963064586","https://openalex.org/W2964084166","https://openalex.org/W2964227577","https://openalex.org/W2973049979","https://openalex.org/W2980402953","https://openalex.org/W4296927107","https://openalex.org/W6631362777","https://openalex.org/W6633301432","https://openalex.org/W6680987062","https://openalex.org/W6690610466","https://openalex.org/W6713286487"],"related_works":["https://openalex.org/W3015944949","https://openalex.org/W3103003256","https://openalex.org/W3099610051","https://openalex.org/W37162924","https://openalex.org/W2143343256","https://openalex.org/W2041509879","https://openalex.org/W3093734877","https://openalex.org/W2981498029","https://openalex.org/W2587942996","https://openalex.org/W1978681480","https://openalex.org/W1566679080","https://openalex.org/W2158273884","https://openalex.org/W269674882","https://openalex.org/W2159501289","https://openalex.org/W2123663504","https://openalex.org/W2147706354","https://openalex.org/W3117722298","https://openalex.org/W1986301630","https://openalex.org/W2542605056","https://openalex.org/W2057826000"],"abstract_inverted_index":{"Reverberation":[0],"negatively":[1],"impacts":[2],"the":[3,14,30,50,117,140,147],"performance":[4,46],"of":[5,16,49,94,146],"automatic":[6],"speech":[7,73,142],"recognition":[8],"(ASR).":[9],"Prior":[10],"work":[11],"on":[12,85],"quantifying":[13],"effect":[15],"reverberation":[17],"has":[18],"shown":[19],"that":[20,25,131],"clarity":[21],"(C50),":[22],"a":[23,60,76,91],"parameter":[24],"can":[26,133],"be":[27,106,114,134],"estimated":[28,135],"from":[29,56,71,139],"acoustic":[31,57,95,148],"impulse":[32,96],"response,":[33],"is":[34],"correlated":[35,108],"with":[36,109,116],"ASR":[37,45,88],"performance.":[38],"In":[39],"this":[40],"paper":[41],"we":[42],"propose":[43],"predicting":[44],"in":[47],"terms":[48],"word":[51],"error":[52],"rate":[53],"(WER)":[54],"directly":[55,138],"parameters":[58],"via":[59],"polynomial,":[61],"sigmoidal,":[62],"or":[63],"neural":[64,78],"network":[65,79],"fit,":[66],"as":[67,69],"well":[68],"blindly":[70],"reverberant":[72,141],"samples":[74,143],"using":[75],"convolutional":[77],"(CNN).":[80],"We":[81],"carry":[82],"out":[83],"experiments":[84],"two":[86],"state-of-the-art":[87],"models":[89],"and":[90,103],"large":[92],"set":[93],"responses":[97],"(AIRs).":[98],"The":[99,121],"results":[100],"confirm":[101],"C50":[102],"C80":[104],"to":[105,113],"highly":[107],"WER,":[110],"allowing":[111],"WER":[112,128,132],"predicted":[115],"proposed":[118,122],"fitting":[119],"approaches.":[120],"non-intrusive":[123],"CNN":[124],"model":[125],"outperforms":[126],"C50-based":[127],"prediction,":[129],"indicating":[130],"blindly,":[136],"i.e.,":[137],"without":[144],"knowledge":[145],"parameters.":[149]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}