{"id":"https://openalex.org/W2517964230","doi":"https://doi.org/10.21437/interspeech.2016-978","title":"Synthesis of Device-Independent Noise Corpora for Realistic ASR Evaluation","display_name":"Synthesis of Device-Independent Noise Corpora for Realistic ASR Evaluation","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2517964230","doi":"https://doi.org/10.21437/interspeech.2016-978","mag":"2517964230"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-978","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5036868085","display_name":"Hannes Gamper","orcid":"https://orcid.org/0000-0002-2148-6367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hannes Gamper","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043982558","display_name":"Mark R. Thomas","orcid":"https://orcid.org/0000-0001-7048-7764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark R.P. Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038552992","display_name":"Lyle Corbin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyle Corbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.021,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77455292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2791","last_page":"2795"},"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/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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7782043218612671},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.7321577668190002},{"id":"https://openalex.org/keywords/directivity","display_name":"Directivity","score":0.7180315256118774},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6586233973503113},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6400735378265381},{"id":"https://openalex.org/keywords/device-under-test","display_name":"Device under test","score":0.6005253791809082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5547800064086914},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4989662170410156},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.410079687833786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34565597772598267},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1681993305683136},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07270157337188721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782043218612671},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.7321577668190002},{"id":"https://openalex.org/C189039984","wikidata":"https://www.wikidata.org/wiki/Q8225412","display_name":"Directivity","level":3,"score":0.7180315256118774},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6586233973503113},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6400735378265381},{"id":"https://openalex.org/C76249512","wikidata":"https://www.wikidata.org/wiki/Q1206780","display_name":"Device under test","level":3,"score":0.6005253791809082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5547800064086914},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4989662170410156},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.410079687833786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34565597772598267},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1681993305683136},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07270157337188721},{"id":"https://openalex.org/C44838205","wikidata":"https://www.wikidata.org/wiki/Q127995","display_name":"Microwave","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-978","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W130191466","https://openalex.org/W1484839547","https://openalex.org/W1487212816","https://openalex.org/W2068815893","https://openalex.org/W2095926185","https://openalex.org/W2160525176","https://openalex.org/W2394932179","https://openalex.org/W2534141673","https://openalex.org/W2600738661"],"related_works":["https://openalex.org/W2610683599","https://openalex.org/W3199097733","https://openalex.org/W1968392023","https://openalex.org/W4389273101","https://openalex.org/W2392511087","https://openalex.org/W2389030363","https://openalex.org/W164431307","https://openalex.org/W2368900153","https://openalex.org/W2742399695","https://openalex.org/W2166250393"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,20,112,156,173,184],"effectively":[3],"evaluate":[4],"the":[5,39,81,87,105,120,136,140,148,167,170,179],"accuracy":[6],"of":[7,30,41,83,91,109,122,134,169,191],"automatic":[8],"speech":[9,101],"recognition":[10],"(ASR)":[11],"with":[12,86,104],"a":[13,22,42,48,58,75,110,114,130,153,189],"novel":[14],"capture":[15],"device,":[16],"it":[17],"is":[18,28,102,127],"important":[19],"create":[21],"realistic":[23,62],"test":[24,45,116,192],"data":[25],"corpus":[26,117],"that":[27,60,77,147],"representative":[29],"real-world":[31],"noise":[32,70,99,198],"conditions.":[33],"Typically,":[34],"this":[35],"involves":[36],"either":[37],"recording":[38,97],"output":[40],"device":[43],"under":[44],"(DUT)":[46],"in":[47,57],"noisy":[49],"environment,":[50],"or":[51],"synthesizing":[52],"an":[53,123],"environment":[54],"over":[55],"loudspeakers":[56],"way":[59],"simulates":[61],"signal-to-noise":[63],"ratios":[64],"(SNRs),":[65],"reverberation":[66],"times,":[67],"and":[68,89,100,139,158,178,197],"spatial":[69,96],"distributions.":[71],"Here":[72],"we":[73],"propose":[74],"method":[76,150,165],"aims":[78],"at":[79],"combining":[80],"realism":[82],"in-situ":[84],"recordings":[85],"convenience":[88],"repeatability":[90],"synthetic":[92,115],"corpora.":[93],"A":[94],"device-independent":[95],"containing":[98],"combined":[103],"measured":[106],"directivity":[107,142],"pattern":[108],"DUT":[111,171],"generate":[113],"for":[118],"evaluating":[119],"performance":[121],"ASR":[124],"system.":[125],"This":[126],"achieved":[128],"by":[129],"spherical":[131],"harmonic":[132],"decomposition":[133],"both":[135],"sound":[137],"field":[138],"DUT\u2019s":[141],"patterns.":[143],"Experimental":[144],"results":[145],"suggest":[146],"proposed":[149,163],"can":[151],"be":[152],"viable":[154],"alternative":[155],"costly":[157],"cumbersome":[159],"device-dependent":[160],"measurements.":[161],"The":[162],"simulation":[164],"predicted":[166],"SNR":[168],"response":[172],"within":[174,185],"about":[175,186],"3":[176],"dB":[177],"word":[180],"error":[181],"rate":[182],"(WER)":[183],"20%,":[187],"across":[188],"range":[190],"SNRs,":[193],"target":[194],"source":[195],"directions,":[196],"types.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}