{"id":"https://openalex.org/W1230632900","doi":"https://doi.org/10.21437/icslp.2002-596","title":"Double the trouble: handling noise and reverberation in far-field automatic speech recognition","display_name":"Double the trouble: handling noise and reverberation in far-field automatic speech recognition","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W1230632900","doi":"https://doi.org/10.21437/icslp.2002-596","mag":"1230632900"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-596","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5113500124","display_name":"David Gelbart","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Gelbart","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113500124"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.4446,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.80820462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2185","last_page":"2188"},"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":0.9994000196456909,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.9087958335876465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8463525176048279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940019726753235},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6761882305145264},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6050657033920288},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5862998962402344},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.469448059797287},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4511028826236725},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.450946569442749},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4493393003940582},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.43980562686920166},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.43820521235466003},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4312272071838379},{"id":"https://openalex.org/keywords/subtraction","display_name":"Subtraction","score":0.42748892307281494},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4220179319381714},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4178144335746765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3489443063735962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33365947008132935},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25444456934928894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.193599134683609},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.112140953540802},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0787905752658844}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9087958335876465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8463525176048279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940019726753235},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6761882305145264},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6050657033920288},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5862998962402344},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.469448059797287},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4511028826236725},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.450946569442749},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4493393003940582},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.43980562686920166},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.43820521235466003},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4312272071838379},{"id":"https://openalex.org/C68060419","wikidata":"https://www.wikidata.org/wiki/Q40754","display_name":"Subtraction","level":2,"score":0.42748892307281494},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4220179319381714},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4178144335746765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3489443063735962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33365947008132935},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25444456934928894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.193599134683609},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.112140953540802},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0787905752658844},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"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":2,"locations":[{"id":"doi:10.21437/icslp.2002-596","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.6948","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.6948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/ftp/global/pub/speech/papers/icslp02-noiseandreverb.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W62589995","https://openalex.org/W186802743","https://openalex.org/W1485532853","https://openalex.org/W1502283197","https://openalex.org/W1677682992","https://openalex.org/W1840695391","https://openalex.org/W2136821271","https://openalex.org/W2137075158","https://openalex.org/W2151484683","https://openalex.org/W2152131029"],"related_works":["https://openalex.org/W2618657287","https://openalex.org/W2380771148","https://openalex.org/W2348931051","https://openalex.org/W2535773091","https://openalex.org/W2538903081","https://openalex.org/W2389562147","https://openalex.org/W2109356272","https://openalex.org/W4386746628","https://openalex.org/W3008816511","https://openalex.org/W2132495960"],"abstract_inverted_index":{"Far-field":[0],"microphone":[1,38],"speech":[2,10,27,59],"signals":[3],"cause":[4],"high":[5],"error":[6,30,120],"rates":[7,31],"for":[8],"automatic":[9],"recognition":[11,28,60,118],"systems,":[12],"due":[13],"to":[14,69,80,96],"room":[15],"reverberation":[16],"and":[17,110],"lower":[18],"signal-to-noise":[19],"ratios.":[20],"We":[21],"have":[22],"observed":[23],"large":[24],"increases":[25],"in":[26,39,43,57,94],"word":[29,119],"when":[32],"using":[33,62],"a":[34,40,63,77,86,104],"far-field":[35,58],"(3-6":[36],"feet)":[37],"conference":[41],"room,":[42],"comparison":[44],"with":[45,98],"recordings":[46],"from":[47],"close-talking":[48],"microphones.":[49],"In":[50],"an":[51],"earlier":[52],"paper,":[53],"we":[54,101],"showed":[55],"improvements":[56],"performance":[61],"longterm":[64,111],"log":[65,112],"spectral":[66,113],"subtraction":[67,83,114],"method":[68,73],"combat":[70],"reverberation.":[71,99],"This":[72],"is":[74],"based":[75],"on":[76],"principle":[78],"similar":[79],"cepstral":[81],"mean":[82],"but":[84],"uses":[85],"much":[87],"longer":[88],"analysis":[89],"window":[90],"(e.g.,":[91],"1":[92],"s)":[93],"order":[95],"deal":[97],"Here":[100],"show":[102],"that":[103],"combination":[105],"of":[106],"short-term":[107],"noise":[108],"filtering":[109],"can":[115],"further":[116],"reduce":[117],"rates.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
