{"id":"https://openalex.org/W1524805189","doi":"https://doi.org/10.21437/icslp.2002-65","title":"Enhanced histogram normalization in the acoustic feature space","display_name":"Enhanced histogram normalization in the acoustic feature space","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W1524805189","doi":"https://doi.org/10.21437/icslp.2002-65","mag":"1524805189"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-65","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-65","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":"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/A5027439626","display_name":"Sirko Molau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sirko Molau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014989854","display_name":"Florian Hilger","orcid":"https://orcid.org/0009-0005-8656-6869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Hilger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066294527","display_name":"Daniel Keysers","orcid":"https://orcid.org/0000-0001-8765-475X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Keysers","raw_affiliation_strings":["[Rwth Aachen University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Rwth Aachen University]","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1421","last_page":"1424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/normalization","display_name":"Normalization (sociology)","score":0.9089678525924683},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.8729475736618042},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6091402769088745},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5837264657020569},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5765459537506104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5662131905555725},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5233256816864014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5162231922149658},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.473205029964447},{"id":"https://openalex.org/keywords/histogram-matching","display_name":"Histogram matching","score":0.46516990661621094},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4312777519226074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2675924301147461},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.22686007618904114}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9089678525924683},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.8729475736618042},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6091402769088745},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5837264657020569},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5765459537506104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5662131905555725},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5233256816864014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5162231922149658},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.473205029964447},{"id":"https://openalex.org/C127449775","wikidata":"https://www.wikidata.org/wiki/Q3785871","display_name":"Histogram matching","level":4,"score":0.46516990661621094},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4312777519226074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2675924301147461},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.22686007618904114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.2002-65","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-65","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:10.1.1.18.2114","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.2114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/PostScript/InterneArbeiten/Molau_Enhanced_Normalization_NormalizationIn_The_Acoustic_Feature_Space_ICSLP_2002.ps","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:111396","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/111396","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W54525843","https://openalex.org/W1854414011","https://openalex.org/W2108134265","https://openalex.org/W2149912780","https://openalex.org/W2168320035"],"related_works":["https://openalex.org/W2021595906","https://openalex.org/W2766087987","https://openalex.org/W1606020025","https://openalex.org/W106304674","https://openalex.org/W2095992409","https://openalex.org/W2357857030","https://openalex.org/W2035826164","https://openalex.org/W2063491684","https://openalex.org/W2038621399","https://openalex.org/W2085219086"],"abstract_inverted_index":{"We":[0,50],"describe":[1],"two":[2],"methods":[3,76],"that":[4,15],"aim":[5],"at":[6,10],"normalizing":[7],"acoustic":[8],"vectors":[9],"the":[11,16,21,27,37,47,81],"filterbank":[12],"level":[13],"such":[14],"test":[17],"data":[18,23],"distribution":[19],"matches":[20],"training":[22,62],"distribution.":[24],"They":[25],"enhance":[26],"histogram":[28,83],"normalization":[29,84],"technique":[30],"proposed":[31],"earlier":[32],"by":[33,45],"taking":[34],"care":[35],"of":[36,54],"variable":[38],"silence":[39],"fraction":[40],"for":[41],"each":[42],"speaker,":[43],"and":[44,63,67,97],"rotating":[46],"feature":[48],"space.":[49],"report":[51],"a":[52],"number":[53],"recognition":[55],"tests":[56],"under":[57],"minor":[58],"(different":[59],"microphones":[60],"in":[61,89],"test,":[64],"telephone":[65],"data)":[66],"major":[68],"(office":[69],"vs.":[70],"car":[71],"recordings)":[72],"mismatch":[73],"conditions.":[74],"Both":[75],"give":[77],"superior":[78],"performance":[79],"to":[80],"basic":[82],"approach.":[85],"The":[86],"overall":[87],"improvements":[88],"word":[90],"error":[91],"rate":[92],"(WER)":[93],"range":[94],"between":[95],"6%":[96],"85%":[98],"relative.":[99]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
