{"id":"https://openalex.org/W2130020166","doi":"https://doi.org/10.1109/icassp.2012.6288821","title":"A novel approach to soft-mask estimation and Log-Spectral enhancement for robust speech recognition","display_name":"A novel approach to soft-mask estimation and Log-Spectral enhancement for robust speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2130020166","doi":"https://doi.org/10.1109/icassp.2012.6288821","mag":"2130020166"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058481276","display_name":"Julien van Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien van Hout","raw_affiliation_strings":["Electrical Engineering Department, University of California, Los Angeles, USA","Electrical Engineering Department, University of California, Los Angeles,,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Electrical Engineering Department, University of California, Los Angeles,,USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112421995","display_name":"Abeer Alwan","orcid":"https://orcid.org/0000-0003-3390-9379"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abeer Alwan","raw_affiliation_strings":["Electrical Engineering Department, University of California, Los Angeles, USA","Electrical Engineering Department, University of California, Los Angeles,,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Electrical Engineering Department, University of California, Los Angeles,,USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":3.172,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93772538,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4105","last_page":"4108"},"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":0.998199999332428,"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":0.6520665884017944},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6491803526878357},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6385284662246704},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5762881636619568},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5166173577308655},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4977257549762726},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4591050148010254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4530309736728668},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42859840393066406},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4191117584705353},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2883569002151489},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19155603647232056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520665884017944},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6491803526878357},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6385284662246704},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5762881636619568},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5166173577308655},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4977257549762726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4591050148010254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4530309736728668},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42859840393066406},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4191117584705353},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2883569002151489},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19155603647232056},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W289804034","https://openalex.org/W1488775899","https://openalex.org/W2088489891","https://openalex.org/W2103202874","https://openalex.org/W2108524362","https://openalex.org/W2120689488","https://openalex.org/W2121973264","https://openalex.org/W2131770202","https://openalex.org/W2134885320","https://openalex.org/W2141520175","https://openalex.org/W2143855671","https://openalex.org/W2145759598","https://openalex.org/W2151484683","https://openalex.org/W2158336491","https://openalex.org/W3147539069","https://openalex.org/W6610316520","https://openalex.org/W6629240969","https://openalex.org/W6682194319"],"related_works":["https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2275432853","https://openalex.org/W197907117","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W1834994814"],"abstract_inverted_index":{"This":[0,70],"paper":[1],"describes":[2],"a":[3,73],"technique":[4],"for":[5],"enhancing":[6],"the":[7,29,41,62,67,86,90,103,123,126,148,153],"Mel-filtered":[8,91],"log":[9],"spectra":[10,105],"of":[11,35,45,75,89,93,106],"noisy":[12,94,110,130],"speech,":[13],"with":[14,141,157],"application":[15],"to":[16,60,65,84,114,121],"noise":[17],"robust":[18],"speech":[19,36,46,111],"recognition.":[20],"We":[21],"first":[22],"compute":[23],"an":[24,33,52,138],"SNR-based":[25],"soft-decision":[26],"mask":[27,50,71],"in":[28,79,125],"Mel-spectral":[30],"domain":[31],"as":[32,51,113],"indicator":[34],"presence.":[37],"Then,":[38],"we":[39,97],"exploit":[40],"known":[42],"time-frequency":[43],"correlation":[44],"by":[47],"treating":[48],"this":[49],"image,":[53],"and":[54,58,64,109,120],"performing":[55],"median":[56],"filtering":[57],"blurring":[59],"remove":[61],"outliers":[63],"smooth":[66],"decision":[68],"regions.":[69],"constitutes":[72],"set":[74],"multiplicative":[76],"coefficients":[77],"(ranging":[78],"[0,1])":[80],"that":[81,152],"are":[82],"used":[83],"discard":[85],"unreliable":[87],"parts":[88],"log-spectrum":[92],"speech.":[95],"Finally,":[96],"apply":[98],"Log-Spectral":[99],"Flooring":[100],"[1]":[101],"on":[102,133,147],"liftered":[104],"both":[107],"clean":[108,144],"so":[112],"match":[115],"their":[116,142],"respective":[117],"dynamic":[118],"ranges":[119],"emphasize":[122],"information":[124],"spectral":[127],"peaks.":[128],"The":[129],"MFCCs":[131],"computed":[132],"these":[134],"modified":[135],"log-spectra":[136],"show":[137],"increased":[139],"similarity":[140],"corresponding":[143],"MFCCs.":[145],"Evaluation":[146],"Aurora-2":[149],"corpus":[150],"shows":[151],"proposed":[154],"approach":[155],"competes":[156],"state-of-the-art":[158],"front-ends,":[159],"like":[160],"ETSI-AFE,":[161],"MVA":[162],"or":[163],"PNCC.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}