{"id":"https://openalex.org/W4301791596","doi":"https://doi.org/10.21437/icslp.1996-506","title":"Spectral estimation and normalisation for robust speech recognition","display_name":"Spectral estimation and normalisation for robust speech recognition","publication_year":1996,"publication_date":"1996-10-03","ids":{"openalex":"https://openalex.org/W4301791596","doi":"https://doi.org/10.21437/icslp.1996-506"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1996-506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-506","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","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/A5057752299","display_name":"Tom Claes","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Tom Claes","raw_affiliation_strings":["U.Leuven -E.S.A.T. Kardinaal Mercierlaan 94 B-3001 Heverlee, Belgium"],"affiliations":[{"raw_affiliation_string":"U.Leuven -E.S.A.T. Kardinaal Mercierlaan 94 B-3001 Heverlee, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785687","display_name":"Fei Xie","orcid":"https://orcid.org/0000-0003-3094-3512"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Fei Xie","raw_affiliation_strings":["U.Leuven -E.S.A.T. Kardinaal Mercierlaan 94 B-3001 Heverlee, Belgium"],"affiliations":[{"raw_affiliation_string":"U.Leuven -E.S.A.T. Kardinaal Mercierlaan 94 B-3001 Heverlee, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041039488","display_name":"Dirk Van Compernolle","orcid":"https://orcid.org/0000-0003-0075-848X"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dirk van Compernolle","raw_affiliation_strings":["U.Leuven -E.S.A.T. Kardinaal Mercierlaan 94 B-3001 Heverlee, Belgium"],"affiliations":[{"raw_affiliation_string":"U.Leuven -E.S.A.T. Kardinaal Mercierlaan 94 B-3001 Heverlee, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057752299"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66666667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1997","last_page":"2000"},"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":0.9983999729156494,"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":0.6656858921051025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.60521399974823},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5548000335693359},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4138803482055664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.408441960811615},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1518450677394867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656858921051025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.60521399974823},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5548000335693359},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4138803482055664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.408441960811615},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1518450677394867},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1996-506","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-506","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1645939","https://openalex.org/W1263530259","https://openalex.org/W1687555731","https://openalex.org/W2109816922","https://openalex.org/W2121603214","https://openalex.org/W2125630648","https://openalex.org/W2137983211","https://openalex.org/W2140977001","https://openalex.org/W4245923654","https://openalex.org/W4300416747"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,100,131],"in":[2,28,57,78],"adverse":[3],"conditions":[4],"remains":[5],"a":[6,29,51,93],"difficult":[7],"but":[8],"challenging":[9],"problem.It":[10],"is":[11,48,55,87,133],"already":[12],"shown":[13],"[1]":[14],"that":[15,63,101],"normalisation":[16],"of":[17,24,60,115],"the":[18,25,37,46,53,58,67,81,85,104,127],"dynamic":[19],"range":[20],"(SNR":[21],"1":[22],")":[23],"frequency":[26],"channels":[27],"mel":[30],"scale":[31],"triangular":[32],"filterbank":[33,82,106,110],"(MFCC)":[34],"[2],":[35],"improves":[36],"robustness":[38],"against":[39],"both":[40],"additive":[41],"and":[42,112],"convolutional":[43],"noise.Nevertheless,":[44],"because":[45],"method":[47],"based":[49],"on":[50,103,126],"masking-technique,":[52],"improvement":[54],"small":[56],"case":[59],"SNR":[61],"values":[62],"are":[64,124],"smaller":[65],"than":[66],"target":[68],"(normalised)":[69],"SNR.A":[70],"solution":[71],"for":[72,98],"this":[73,89],"problem":[74],"can":[75],"be":[76],"found":[77],"first":[79],"enhancing":[80],"energies":[83,111],"before":[84],"masking-technique":[86],"applied.For":[88],"purpose":[90],"we":[91],"developed":[92],"Non-linear":[94],"Spectral":[95],"Estimator":[96],"(NSE)":[97],"speech":[99],"operates":[102],"log":[105],"energies.NSE":[107],"enhances":[108],"these":[109],"makes":[113],"use":[114],"SNR-normalisation":[116],"also":[117],"effective":[118],"at":[119,136],"very":[120],"low":[121],"SNRs.Experimental":[122],"results":[123],"given":[125],"NOISEX-92":[128],"[3]":[129],"database.Better":[130],"performance":[132],"seen":[134],"even":[135],"0dB":[137],"SNR.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
